Toggle Poster Visibility
Expo Demonstration
Sun Jul 17 09:00 AM -- 02:00 PM (PDT) @ Room 310 None
TorchRL: the PyTorch RL Domain library
Expo Workshop
Sun Jul 17 09:00 AM -- 11:50 AM (PDT) @ Room 301
Real World RL with Vowpal Wabbit and Azure Personalizer
Tutorial
Mon Jul 18 10:00 AM -- 12:00 PM (PDT) @ Ballroom 1 & 2 None
Bridging Learning and Decision Making
Session
Tue Jul 19 07:30 AM -- 09:00 AM (PDT) @ Hall F None
Reinforcement Learning
Spotlight
Tue Jul 19 07:30 AM -- 07:35 AM (PDT) @ Hall F
Dynamic Regret of Online Markov Decision Processes
Spotlight
Tue Jul 19 07:35 AM -- 07:40 AM (PDT) @ Hall F
On the Impossibility of Learning to Cooperate with Adaptive Partner Strategies in Repeated Games
Spotlight
Tue Jul 19 07:40 AM -- 07:45 AM (PDT) @ Hall F
Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning
Spotlight
Tue Jul 19 07:45 AM -- 07:50 AM (PDT) @ Hall F
Provable Reinforcement Learning with a Short-Term Memory
[
Paper PDF]
Spotlight
Tue Jul 19 07:50 AM -- 07:55 AM (PDT) @ Hall F
Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer
[
Paper PDF]
Spotlight
Tue Jul 19 07:55 AM -- 08:00 AM (PDT) @ Hall F
Mirror Learning: A Unifying Framework of Policy Optimisation
Oral
Tue Jul 19 08:00 AM -- 08:20 AM (PDT) @ Hall F
Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDP
Spotlight
Tue Jul 19 08:20 AM -- 08:25 AM (PDT) @ Hall F
Learning Infinite-horizon Average-reward Markov Decision Process with Constraints
Spotlight
Tue Jul 19 08:25 AM -- 08:30 AM (PDT) @ Hall F
A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning
Spotlight
Tue Jul 19 08:30 AM -- 08:35 AM (PDT) @ Hall F
Langevin Monte Carlo for Contextual Bandits
Spotlight
Tue Jul 19 08:35 AM -- 08:40 AM (PDT) @ Hall F
Prompting Decision Transformer for Few-Shot Policy Generalization
Spotlight
Tue Jul 19 08:40 AM -- 08:45 AM (PDT) @ Room 301 - 303
Generative Cooperative Networks for Natural Language Generation
Spotlight
Tue Jul 19 08:40 AM -- 08:45 AM (PDT) @ Hall F
Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning
Spotlight
Tue Jul 19 08:45 AM -- 08:50 AM (PDT) @ Hall F
Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation
Oral
Tue Jul 19 10:30 AM -- 10:50 AM (PDT) @ Room 318 - 320
Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning
In
Optimization
Oral
Tue Jul 19 10:30 AM -- 10:50 AM (PDT) @ Room 309
Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution
Session
Tue Jul 19 10:30 AM -- 12:00 PM (PDT) @ Room 309 None
Reinforcement Learning: Deep/Batch/Offline
Spotlight
Tue Jul 19 10:50 AM -- 10:55 AM (PDT) @ Room 309
AnyMorph: Learning Transferable Polices By Inferring Agent Morphology
Spotlight
Tue Jul 19 10:50 AM -- 10:55 AM (PDT) @ Room 301 - 303
Meta-Learning Hypothesis Spaces for Sequential Decision-making
Spotlight
Tue Jul 19 10:55 AM -- 11:00 AM (PDT) @ Room 310
Policy Gradient Method For Robust Reinforcement Learning
Spotlight
Tue Jul 19 10:55 AM -- 11:00 AM (PDT) @ Room 309
DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations
Spotlight
Tue Jul 19 11:00 AM -- 11:05 AM (PDT) @ Room 309
Stabilizing Off-Policy Deep Reinforcement Learning from Pixels
Oral
Tue Jul 19 11:05 AM -- 11:25 AM (PDT) @ Ballroom 3 & 4
Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four
Spotlight
Tue Jul 19 11:05 AM -- 11:10 AM (PDT) @ Room 309
Influence-Augmented Local Simulators: a Scalable Solution for Fast Deep RL in Large Networked Systems
Spotlight
Tue Jul 19 11:10 AM -- 11:15 AM (PDT) @ Room 309
CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer
Oral
Tue Jul 19 11:15 AM -- 11:35 AM (PDT) @ Room 309
Offline RL Policies Should Be Trained to be Adaptive
Spotlight
Tue Jul 19 11:35 AM -- 11:40 AM (PDT) @ Room 309
Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control
Spotlight
Tue Jul 19 11:40 AM -- 11:45 AM (PDT) @ Room 309
PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration
Spotlight
Tue Jul 19 11:45 AM -- 11:50 AM (PDT) @ Room 309
Supervised Off-Policy Ranking
Spotlight
Tue Jul 19 11:50 AM -- 11:55 AM (PDT) @ Room 309
The Primacy Bias in Deep Reinforcement Learning
Spotlight
Tue Jul 19 11:55 AM -- 12:00 PM (PDT) @ Room 309
Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning
Spotlight
Tue Jul 19 01:20 PM -- 01:25 PM (PDT) @ Room 318 - 320
Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning
Spotlight
Tue Jul 19 01:25 PM -- 01:30 PM (PDT) @ Room 318 - 320
Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation
Spotlight
Tue Jul 19 01:30 PM -- 01:35 PM (PDT) @ Room 318 - 320
Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning
Spotlight
Tue Jul 19 01:35 PM -- 01:40 PM (PDT) @ Room 318 - 320
Scalable Deep Reinforcement Learning Algorithms for Mean Field Games
Spotlight
Tue Jul 19 01:40 PM -- 01:45 PM (PDT) @ Room 318 - 320
Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning
Oral
Tue Jul 19 01:45 PM -- 02:05 PM (PDT) @ Room 318 - 320
Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence
Spotlight
Tue Jul 19 01:45 PM -- 01:50 PM (PDT) @ Ballroom 1 & 2
Training Discrete Deep Generative Models via Gapped Straight-Through Estimator
Spotlight
Tue Jul 19 02:05 PM -- 02:10 PM (PDT) @ Room 318 - 320
Self-Organized Polynomial-Time Coordination Graphs
Spotlight
Tue Jul 19 02:10 PM -- 02:15 PM (PDT) @ Room 318 - 320
Individual Reward Assisted Multi-Agent Reinforcement Learning
Spotlight
Tue Jul 19 02:25 PM -- 02:30 PM (PDT) @ Room 318 - 320
Deconfounded Value Decomposition for Multi-Agent Reinforcement Learning
Spotlight
Tue Jul 19 02:30 PM -- 02:35 PM (PDT) @ Room 318 - 320
Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #131
Generative Cooperative Networks for Natural Language Generation
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #437
Training Discrete Deep Generative Models via Gapped Straight-Through Estimator
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #529
Meta-Learning Hypothesis Spaces for Sequential Decision-making
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #635
Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #804
Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #806
Provable Reinforcement Learning with a Short-Term Memory
[
Paper PDF]
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #808
Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #810
Mirror Learning: A Unifying Framework of Policy Optimisation
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #816
A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #820
Prompting Decision Transformer for Few-Shot Policy Generalization
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #822
Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #824
Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #826
Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #828
AnyMorph: Learning Transferable Polices By Inferring Agent Morphology
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #830
DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #832
Stabilizing Off-Policy Deep Reinforcement Learning from Pixels
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #834
Influence-Augmented Local Simulators: a Scalable Solution for Fast Deep RL in Large Networked Systems
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #836
CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #835
PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #829
The Primacy Bias in Deep Reinforcement Learning
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #827
Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #823
Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #821
Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #819
Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning
[
Paper PDF]
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #817
Scalable Deep Reinforcement Learning Algorithms for Mean Field Games
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #815
Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #813
Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #811
Self-Organized Polynomial-Time Coordination Graphs
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #809
Individual Reward Assisted Multi-Agent Reinforcement Learning
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #803
Deconfounded Value Decomposition for Multi-Agent Reinforcement Learning
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #801
Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #915
Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #1121
Policy Gradient Method For Robust Reinforcement Learning
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #1217
Cooperative Online Learning in Stochastic and Adversarial MDPs
Poster
Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #1209
Nearly Optimal Policy Optimization with Stable at Any Time Guarantee
Session
Wed Jul 20 07:30 AM -- 09:00 AM (PDT) @ Room 307 None
Reinforcement Learning: Deep RL
Spotlight
Wed Jul 20 07:30 AM -- 07:35 AM (PDT) @ Room 307
Modeling Strong and Human-Like Gameplay with KL-Regularized Search
Spotlight
Wed Jul 20 07:35 AM -- 07:40 AM (PDT) @ Room 307
Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters
Spotlight
Wed Jul 20 07:40 AM -- 07:45 AM (PDT) @ Room 307
Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning
Spotlight
Wed Jul 20 07:45 AM -- 07:50 AM (PDT) @ Room 307
Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search
Spotlight
Wed Jul 20 07:50 AM -- 07:55 AM (PDT) @ Room 310
The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces
Spotlight
Wed Jul 20 07:50 AM -- 07:55 AM (PDT) @ Room 307
Generalized Data Distribution Iteration
Spotlight
Wed Jul 20 07:55 AM -- 08:00 AM (PDT) @ Room 310
Extracting Latent State Representations with Linear Dynamics from Rich Observations
Spotlight
Wed Jul 20 07:55 AM -- 08:00 AM (PDT) @ Room 307
Optimizing Tensor Network Contraction Using Reinforcement Learning
[
Paper PDF]
Spotlight
Wed Jul 20 08:00 AM -- 08:05 AM (PDT) @ Room 307
History Compression via Language Models in Reinforcement Learning
Oral
Wed Jul 20 08:05 AM -- 08:25 AM (PDT) @ Room 307
REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer
Spotlight
Wed Jul 20 08:05 AM -- 08:10 AM (PDT) @ Room 310
Consensus Multiplicative Weights Update: Learning to Learn using Projector-based Game Signatures
Spotlight
Wed Jul 20 08:25 AM -- 08:30 AM (PDT) @ Room 307
LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation
Spotlight
Wed Jul 20 08:30 AM -- 08:35 AM (PDT) @ Room 307
Efficient Learning for AlphaZero via Path Consistency
Spotlight
Wed Jul 20 08:35 AM -- 08:40 AM (PDT) @ Room 307
A data-driven approach for learning to control computers
Spotlight
Wed Jul 20 08:40 AM -- 08:45 AM (PDT) @ Room 310
Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation
Spotlight
Wed Jul 20 08:40 AM -- 08:45 AM (PDT) @ Room 307
Zero-Shot Reward Specification via Grounded Natural Language
Spotlight
Wed Jul 20 08:45 AM -- 08:50 AM (PDT) @ Room 307
How to Stay Curious while avoiding Noisy TVs using Aleatoric Uncertainty Estimation
Spotlight
Wed Jul 20 08:50 AM -- 08:55 AM (PDT) @ Room 310
Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
[
Paper PDF]
Spotlight
Wed Jul 20 08:50 AM -- 08:55 AM (PDT) @ Room 307
Model-Value Inconsistency as a Signal for Epistemic Uncertainty
Spotlight
Wed Jul 20 08:55 AM -- 09:00 AM (PDT) @ Room 307
Improving Policy Optimization with Generalist-Specialist Learning
Session
Wed Jul 20 10:15 AM -- 11:45 AM (PDT) @ Room 307 None
Reinforcement Learning
Spotlight
Wed Jul 20 10:15 AM -- 10:20 AM (PDT) @ Room 307
Biased Gradient Estimate with Drastic Variance Reduction for Meta Reinforcement Learning
Spotlight
Wed Jul 20 10:20 AM -- 10:25 AM (PDT) @ Room 307
Analysis of Stochastic Processes through Replay Buffers
Spotlight
Wed Jul 20 10:25 AM -- 10:30 AM (PDT) @ Hall G
DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck
Spotlight
Wed Jul 20 10:25 AM -- 10:30 AM (PDT) @ Room 307
Cascaded Gaps: Towards Logarithmic Regret for Risk-Sensitive Reinforcement Learning
[
Paper PDF]
Spotlight
Wed Jul 20 10:30 AM -- 10:35 AM (PDT) @ Room 307
Communicating via Markov Decision Processes
Spotlight
Wed Jul 20 10:35 AM -- 10:40 AM (PDT) @ Room 307
PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation
Spotlight
Wed Jul 20 10:35 AM -- 10:40 AM (PDT) @ Hall F
LIMO: Latent Inceptionism for Targeted Molecule Generation
Spotlight
Wed Jul 20 10:40 AM -- 10:45 AM (PDT) @ Room 307
DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning
Oral
Wed Jul 20 10:45 AM -- 11:05 AM (PDT) @ Room 307
Planning with Diffusion for Flexible Behavior Synthesis
Spotlight
Wed Jul 20 10:55 AM -- 11:00 AM (PDT) @ Room 301 - 303
Optimizing Sequential Experimental Design with Deep Reinforcement Learning
Spotlight
Wed Jul 20 11:05 AM -- 11:10 AM (PDT) @ Room 307
A Temporal-Difference Approach to Policy Gradient Estimation
Spotlight
Wed Jul 20 11:10 AM -- 11:15 AM (PDT) @ Room 307
MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer
Spotlight
Wed Jul 20 11:15 AM -- 11:20 AM (PDT) @ Room 307
Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency
[
Paper PDF]
Spotlight
Wed Jul 20 11:20 AM -- 11:25 AM (PDT) @ Room 307
Actor-Critic based Improper Reinforcement Learning
Spotlight
Wed Jul 20 11:25 AM -- 11:30 AM (PDT) @ Room 307
On the Sample Complexity of Learning Infinite-horizon Discounted Linear Kernel MDPs
Spotlight
Wed Jul 20 11:30 AM -- 11:35 AM (PDT) @ Room 307
The Geometry of Robust Value Functions
[
Paper PDF]
Spotlight
Wed Jul 20 11:35 AM -- 11:40 AM (PDT) @ Room 307
Denoised MDPs: Learning World Models Better Than the World Itself
Spotlight
Wed Jul 20 11:35 AM -- 11:40 AM (PDT) @ Room 310
A Modern Self-Referential Weight Matrix That Learns to Modify Itself
Spotlight
Wed Jul 20 11:40 AM -- 11:45 AM (PDT) @ Room 310
Short-Term Plasticity Neurons Learning to Learn and Forget
Session
Wed Jul 20 01:30 PM -- 03:05 PM (PDT) @ Hall G None
Reinforcement Learning
Session
Wed Jul 20 01:30 PM -- 03:00 PM (PDT) @ Room 318 - 320 None
Miscellaneous Aspects of Machine Learning/Reinforcement Learning
Spotlight
Wed Jul 20 01:30 PM -- 01:35 PM (PDT) @ Hall G
Greedy based Value Representation for Optimal Coordination in Multi-agent Reinforcement Learning
[
Paper PDF]
Spotlight
Wed Jul 20 01:30 PM -- 01:35 PM (PDT) @ Room 318 - 320
Gradient Descent on Neurons and its Link to Approximate Second-order Optimization
[
Paper PDF]
Spotlight
Wed Jul 20 01:30 PM -- 01:35 PM (PDT) @ Room 307
Improved Regret for Differentially Private Exploration in Linear MDP
Spotlight
Wed Jul 20 01:35 PM -- 01:40 PM (PDT) @ Hall G
Bayesian Nonparametrics for Offline Skill Discovery
Spotlight
Wed Jul 20 01:35 PM -- 01:40 PM (PDT) @ Room 318 - 320
A Tree-based Model Averaging Approach for Personalized Treatment Effect Estimation from Heterogeneous Data Sources
Spotlight
Wed Jul 20 01:40 PM -- 01:45 PM (PDT) @ Hall G
Convergence of Policy Gradient for Entropy Regularized MDPs with Neural Network Approximation in the Mean-Field Regime
Spotlight
Wed Jul 20 01:40 PM -- 01:45 PM (PDT) @ Room 318 - 320
Efficient Online ML API Selection for Multi-Label Classification Tasks
Spotlight
Wed Jul 20 01:40 PM -- 01:45 PM (PDT) @ Room 309
The State of Sparse Training in Deep Reinforcement Learning
Spotlight
Wed Jul 20 01:45 PM -- 01:50 PM (PDT) @ Hall G
Curriculum Reinforcement Learning via Constrained Optimal Transport
Spotlight
Wed Jul 20 01:45 PM -- 01:50 PM (PDT) @ Room 318 - 320
Entropic Causal Inference: Graph Identifiability
Spotlight
Wed Jul 20 01:50 PM -- 01:55 PM (PDT) @ Hall G
Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs
Spotlight
Wed Jul 20 01:50 PM -- 01:55 PM (PDT) @ Room 318 - 320
Architecture Agnostic Federated Learning for Neural Networks
Spotlight
Wed Jul 20 01:55 PM -- 02:00 PM (PDT) @ Ballroom 1 & 2
Geometric Multimodal Contrastive Representation Learning
Spotlight
Wed Jul 20 01:55 PM -- 02:00 PM (PDT) @ Hall F
SDQ: Stochastic Differentiable Quantization with Mixed Precision
In
Applications
Spotlight
Wed Jul 20 01:55 PM -- 02:00 PM (PDT) @ Room 327 - 329
Generalizing Gaussian Smoothing for Random Search
Spotlight
Wed Jul 20 01:55 PM -- 02:00 PM (PDT) @ Hall G
Stabilizing Q-learning with Linear Architectures for Provable Efficient Learning
Spotlight
Wed Jul 20 01:55 PM -- 02:00 PM (PDT) @ Room 318 - 320
Conformal Prediction Sets with Limited False Positives
Spotlight
Wed Jul 20 02:00 PM -- 02:05 PM (PDT) @ Room 318 - 320
Scalable Computation of Causal Bounds
Spotlight
Wed Jul 20 02:00 PM -- 02:05 PM (PDT) @ Hall G
Constrained Offline Policy Optimization
Oral
Wed Jul 20 02:05 PM -- 02:25 PM (PDT) @ Hall G
Causal Dynamics Learning for Task-Independent State Abstraction
Oral
Wed Jul 20 02:05 PM -- 02:25 PM (PDT) @ Room 318 - 320
LIDL: Local Intrinsic Dimension Estimation Using Approximate Likelihood
Spotlight
Wed Jul 20 02:25 PM -- 02:30 PM (PDT) @ Hall G
Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity
Spotlight
Wed Jul 20 02:25 PM -- 02:30 PM (PDT) @ Room 318 - 320
Learning Pseudometric-based Action Representations for Offline Reinforcement Learning
Spotlight
Wed Jul 20 02:30 PM -- 02:35 PM (PDT) @ Hall G
Reinforcement Learning with Action-Free Pre-Training from Videos
Spotlight
Wed Jul 20 02:30 PM -- 02:35 PM (PDT) @ Room 318 - 320
A Statistical Manifold Framework for Point Cloud Data
Spotlight
Wed Jul 20 02:35 PM -- 02:40 PM (PDT) @ Hall F
Symmetric Machine Theory of Mind
In
Applications
Spotlight
Wed Jul 20 02:35 PM -- 02:40 PM (PDT) @ Room 318 - 320
HyperImpute: Generalized Iterative Imputation with Automatic Model Selection
Spotlight
Wed Jul 20 02:35 PM -- 02:40 PM (PDT) @ Hall G
Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods
[
Paper PDF]
Spotlight
Wed Jul 20 02:40 PM -- 02:45 PM (PDT) @ Room 318 - 320
A Natural Actor-Critic Framework for Zero-Sum Markov Games
Spotlight
Wed Jul 20 02:40 PM -- 02:45 PM (PDT) @ Hall G
Delayed Reinforcement Learning by Imitation
Spotlight
Wed Jul 20 02:45 PM -- 02:50 PM (PDT) @ Room 318 - 320
Distributionally Robust $Q$-Learning
Spotlight
Wed Jul 20 02:45 PM -- 02:50 PM (PDT) @ Hall G
Reachability Constrained Reinforcement Learning
Spotlight
Wed Jul 20 02:50 PM -- 02:55 PM (PDT) @ Room 318 - 320
Sparsity in Partially Controllable Linear Systems
[
Paper PDF]
Spotlight
Wed Jul 20 02:50 PM -- 02:55 PM (PDT) @ Hall G
Adaptive Model Design for Markov Decision Process
Spotlight
Wed Jul 20 02:55 PM -- 03:00 PM (PDT) @ Room 318 - 320
Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation
Spotlight
Wed Jul 20 02:55 PM -- 03:00 PM (PDT) @ Hall G
Goal Misgeneralization in Deep Reinforcement Learning
Spotlight
Wed Jul 20 03:00 PM -- 03:05 PM (PDT) @ Hall G None
Translating Robot Skills: Learning Unsupervised Skill Correspondences Across Robots
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #123
LIMO: Latent Inceptionism for Targeted Molecule Generation
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #218
SDQ: Stochastic Differentiable Quantization with Mixed Precision
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #228
Symmetric Machine Theory of Mind
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #434
A Modern Self-Referential Weight Matrix That Learns to Modify Itself
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #436
Short-Term Plasticity Neurons Learning to Learn and Forget
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #431
Geometric Multimodal Contrastive Representation Learning
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #522
The State of Sparse Training in Deep Reinforcement Learning
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #618
DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #623
Learning Pseudometric-based Action Representations for Offline Reinforcement Learning
[
Paper PDF]
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #732
Generalizing Gaussian Smoothing for Random Search
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #802
Optimizing Sequential Experimental Design with Deep Reinforcement Learning
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #818
Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #820
Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #822
Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search
[
Paper PDF]
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) #824
Generalized Data Distribution Iteration
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #826
Optimizing Tensor Network Contraction Using Reinforcement Learning
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #828
History Compression via Language Models in Reinforcement Learning
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #832
LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #834
Efficient Learning for AlphaZero via Path Consistency
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #836
A data-driven approach for learning to control computers
[
Paper PDF]
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #838
Zero-Shot Reward Specification via Grounded Natural Language
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #835
Model-Value Inconsistency as a Signal for Epistemic Uncertainty
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #833
Improving Policy Optimization with Generalist-Specialist Learning
[
Paper PDF]
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #829
Biased Gradient Estimate with Drastic Variance Reduction for Meta Reinforcement Learning
[
Paper PDF]
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #827
Analysis of Stochastic Processes through Replay Buffers
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #825
Cascaded Gaps: Towards Logarithmic Regret for Risk-Sensitive Reinforcement Learning
[
Paper PDF]
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #823
Communicating via Markov Decision Processes
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #819
DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #817
Planning with Diffusion for Flexible Behavior Synthesis
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #813
MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #811
Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #809
Actor-Critic based Improper Reinforcement Learning
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #807
On the Sample Complexity of Learning Infinite-horizon Discounted Linear Kernel MDPs
[
Paper PDF]
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #805
The Geometry of Robust Value Functions
[
Paper PDF]
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #803
Denoised MDPs: Learning World Models Better Than the World Itself
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #801
Greedy based Value Representation for Optimal Coordination in Multi-agent Reinforcement Learning
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #900
Bayesian Nonparametrics for Offline Skill Discovery
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #904
Curriculum Reinforcement Learning via Constrained Optimal Transport
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #908
Stabilizing Q-learning with Linear Architectures for Provable Efficient Learning
[
Paper PDF]
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #912
Causal Dynamics Learning for Task-Independent State Abstraction
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #914
Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #916
Reinforcement Learning with Action-Free Pre-Training from Videos
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #918
Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #920
Delayed Reinforcement Learning by Imitation
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) #922
Reachability Constrained Reinforcement Learning
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #926
Goal Misgeneralization in Deep Reinforcement Learning
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #930
Distributionally Robust $Q$-Learning
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Virtual #934
Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #1020
Improved Regret for Differentially Private Exploration in Linear MDP
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #1119
The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #1117
Extracting Latent State Representations with Linear Dynamics from Rich Observations
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #1113
Consensus Multiplicative Weights Update: Learning to Learn using Projector-based Game Signatures
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #1101
Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #1206
Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
Poster
Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #1212
Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control
Oral
Thu Jul 21 07:30 AM -- 07:50 AM (PDT) @ Hall G None
The Importance of Non-Markovianity in Maximum State Entropy Exploration
Oral
Thu Jul 21 07:30 AM -- 07:50 AM (PDT) @ Ballroom 3 & 4
First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach
Oral
Thu Jul 21 07:30 AM -- 07:50 AM (PDT) @ Room 307
Federated Reinforcement Learning: Linear Speedup Under Markovian Sampling
Session
Thu Jul 21 07:30 AM -- 09:00 AM (PDT) @ Ballroom 3 & 4 None
T: Bandits/Online Learning/Reinforcement Learning
Session
Thu Jul 21 07:30 AM -- 09:00 AM (PDT) @ Hall G None
Reinforcement Learning
Session
Thu Jul 21 07:30 AM -- 09:00 AM (PDT) @ Room 310 None
Optimization/Reinforcement Learning
Spotlight
Thu Jul 21 07:30 AM -- 07:35 AM (PDT) @ Room 310
Adapting k-means Algorithms for Outliers
[
Paper PDF]
Spotlight
Thu Jul 21 07:35 AM -- 07:40 AM (PDT) @ Room 310
Accelerated, Optimal and Parallel: Some results on model-based stochastic optimization
Spotlight
Thu Jul 21 07:40 AM -- 07:45 AM (PDT) @ Room 310
Online Algorithms with Multiple Predictions
Spotlight
Thu Jul 21 07:45 AM -- 07:50 AM (PDT) @ Room 310
Parsimonious Learning-Augmented Caching
Spotlight
Thu Jul 21 07:50 AM -- 07:55 AM (PDT) @ Hall G
Continuous Control with Action Quantization from Demonstrations
[
Paper PDF]
Spotlight
Thu Jul 21 07:50 AM -- 07:55 AM (PDT) @ Ballroom 3 & 4
Generic Coreset for Scalable Learning of Monotonic Kernels: Logistic Regression, Sigmoid and more
Spotlight
Thu Jul 21 07:50 AM -- 07:55 AM (PDT) @ Room 310
RUMs from Head-to-Head Contests
Spotlight
Thu Jul 21 07:55 AM -- 08:00 AM (PDT) @ Ballroom 3 & 4
Shuffle Private Linear Contextual Bandits
Spotlight
Thu Jul 21 07:55 AM -- 08:00 AM (PDT) @ Hall G
Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization
[
Paper PDF]
Spotlight
Thu Jul 21 07:55 AM -- 08:00 AM (PDT) @ Room 310
Quant-BnB: A Scalable Branch-and-Bound Method for Optimal Decision Trees with Continuous Features
Spotlight
Thu Jul 21 08:00 AM -- 08:05 AM (PDT) @ Ballroom 3 & 4
Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity
Spotlight
Thu Jul 21 08:00 AM -- 08:05 AM (PDT) @ Hall G
Inverse Contextual Bandits: Learning How Behavior Evolves over Time
[
Paper PDF]
Spotlight
Thu Jul 21 08:00 AM -- 08:05 AM (PDT) @ Room 310
Robustness in Multi-Objective Submodular Optimization: a Quantile Approach
Oral
Thu Jul 21 08:05 AM -- 08:25 AM (PDT) @ Room 310
The Unsurprising Effectiveness of Pre-Trained Vision Models for Control
Spotlight
Thu Jul 21 08:05 AM -- 08:10 AM (PDT) @ Hall G
Balancing Sample Efficiency and Suboptimality in Inverse Reinforcement Learning
Spotlight
Thu Jul 21 08:05 AM -- 08:10 AM (PDT) @ Ballroom 3 & 4
Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes
Oral
Thu Jul 21 08:10 AM -- 08:30 AM (PDT) @ Ballroom 3 & 4
Label Ranking through Nonparametric Regression
Spotlight
Thu Jul 21 08:10 AM -- 08:15 AM (PDT) @ Hall G
Towards Uniformly Superhuman Autonomy via Subdominance Minimization
Oral
Thu Jul 21 08:15 AM -- 08:35 AM (PDT) @ Hall G
Causal Imitation Learning under Temporally Correlated Noise
Spotlight
Thu Jul 21 08:25 AM -- 08:30 AM (PDT) @ Room 310
COLA: Consistent Learning with Opponent-Learning Awareness
Spotlight
Thu Jul 21 08:30 AM -- 08:35 AM (PDT) @ Ballroom 3 & 4
Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost
Spotlight
Thu Jul 21 08:30 AM -- 08:35 AM (PDT) @ Room 310
A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games
[
Paper PDF]
Spotlight
Thu Jul 21 08:35 AM -- 08:40 AM (PDT) @ Ballroom 3 & 4
A Simple Unified Framework for High Dimensional Bandit Problems
Spotlight
Thu Jul 21 08:35 AM -- 08:40 AM (PDT) @ Hall G
Interactive Inverse Reinforcement Learning for Cooperative Games
Spotlight
Thu Jul 21 08:35 AM -- 08:40 AM (PDT) @ Room 310
A Framework for Learning to Request Rich and Contextually Useful Information from Humans
Spotlight
Thu Jul 21 08:35 AM -- 08:40 AM (PDT) @ Room 301 - 303
Neuro-Symbolic Hierarchical Rule Induction
Spotlight
Thu Jul 21 08:40 AM -- 08:45 AM (PDT) @ Ballroom 3 & 4 None
A Reduction from Linear Contextual Bandits Lower Bounds to Estimations Lower Bounds
Spotlight
Thu Jul 21 08:40 AM -- 08:45 AM (PDT) @ Hall G
A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines
Spotlight
Thu Jul 21 08:40 AM -- 08:45 AM (PDT) @ Room 310
Learning Stochastic Shortest Path with Linear Function Approximation
Spotlight
Thu Jul 21 08:45 AM -- 08:50 AM (PDT) @ Ballroom 3 & 4
Branching Reinforcement Learning
Spotlight
Thu Jul 21 08:45 AM -- 08:50 AM (PDT) @ Hall G
Robust Imitation Learning against Variations in Environment Dynamics
Spotlight
Thu Jul 21 08:45 AM -- 08:50 AM (PDT) @ Room 310
Difference Advantage Estimation for Multi-Agent Policy Gradients
Spotlight
Thu Jul 21 08:50 AM -- 08:55 AM (PDT) @ Ballroom 3 & 4
Fast rates for noisy interpolation require rethinking the effect of inductive bias
Spotlight
Thu Jul 21 08:50 AM -- 08:55 AM (PDT) @ Hall G
Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations
Spotlight
Thu Jul 21 08:50 AM -- 08:55 AM (PDT) @ Room 310
Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification
Spotlight
Thu Jul 21 08:55 AM -- 09:00 AM (PDT) @ Hall G
Learning from Demonstration: Provably Efficient Adversarial Policy Imitation with Linear Function Approximation
Spotlight
Thu Jul 21 08:55 AM -- 09:00 AM (PDT) @ Ballroom 3 & 4
Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path
Spotlight
Thu Jul 21 08:55 AM -- 09:00 AM (PDT) @ Room 310
Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets
[
Paper PDF]
Oral
Thu Jul 21 10:30 AM -- 10:50 AM (PDT) @ Room 318 - 320
Streaming Algorithm for Monotone k-Submodular Maximization with Cardinality Constraints
Oral
Thu Jul 21 10:30 AM -- 10:50 AM (PDT) @ Room 301 - 303
Learning Bellman Complete Representations for Offline Policy Evaluation
Oral
Thu Jul 21 10:30 AM -- 10:50 AM (PDT) @ Room 327 - 329
Generalised Policy Improvement with Geometric Policy Composition
Session
Thu Jul 21 10:30 AM -- 12:00 PM (PDT) @ Room 301 - 303 None
Reinforcement Learning
Session
Thu Jul 21 10:30 AM -- 12:00 PM (PDT) @ Room 318 - 320 None
Optimization/Reinforcement Learning
Session
Thu Jul 21 10:30 AM -- 12:00 PM (PDT) @ Room 327 - 329 None
Reinforcement Learning
Spotlight
Thu Jul 21 10:50 AM -- 10:55 AM (PDT) @ Room 327 - 329
Offline Meta-Reinforcement Learning with Online Self-Supervision
Spotlight
Thu Jul 21 10:50 AM -- 10:55 AM (PDT) @ Room 318 - 320
Adaptive Accelerated (Extra-)Gradient Methods with Variance Reduction
Spotlight
Thu Jul 21 10:50 AM -- 10:55 AM (PDT) @ Room 301 - 303
Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning
Spotlight
Thu Jul 21 10:55 AM -- 11:00 AM (PDT) @ Room 327 - 329
Divergence-Regularized Multi-Agent Actor-Critic
[
Paper PDF]
Spotlight
Thu Jul 21 10:55 AM -- 11:00 AM (PDT) @ Room 318 - 320
Adaptive Second Order Coresets for Data-efficient Machine Learning
Spotlight
Thu Jul 21 10:55 AM -- 11:00 AM (PDT) @ Room 301 - 303
A Simple Reward-free Approach to Constrained Reinforcement Learning
[
Paper PDF]
Spotlight
Thu Jul 21 10:55 AM -- 11:00 AM (PDT) @ Hall G
Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning
In
Applications
[
Paper PDF]
Spotlight
Thu Jul 21 11:00 AM -- 11:05 AM (PDT) @ Room 327 - 329
Understanding Policy Gradient Algorithms: A Sensitivity-Based Approach
Spotlight
Thu Jul 21 11:00 AM -- 11:05 AM (PDT) @ Room 318 - 320
Nesterov Accelerated Shuffling Gradient Method for Convex Optimization
Spotlight
Thu Jul 21 11:00 AM -- 11:05 AM (PDT) @ Room 301 - 303
Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching
Spotlight
Thu Jul 21 11:00 AM -- 11:05 AM (PDT) @ Room 307
Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning
Oral
Thu Jul 21 11:05 AM -- 11:25 AM (PDT) @ Hall G None
Do Differentiable Simulators Give Better Policy Gradients?
In
Applications
Oral
Thu Jul 21 11:05 AM -- 11:25 AM (PDT) @ Hall F
Toward Compositional Generalization in Object-Oriented World Modeling
Spotlight
Thu Jul 21 11:05 AM -- 11:10 AM (PDT) @ Room 327 - 329
Off-Policy Reinforcement Learning with Delayed Rewards
Spotlight
Thu Jul 21 11:05 AM -- 11:10 AM (PDT) @ Room 301 - 303
Temporal Difference Learning for Model Predictive Control
Spotlight
Thu Jul 21 11:05 AM -- 11:10 AM (PDT) @ Room 318 - 320
Efficient Low Rank Convex Bounds for Pairwise Discrete Graphical Models
Oral
Thu Jul 21 11:10 AM -- 11:30 AM (PDT) @ Room 318 - 320
Deletion Robust Submodular Maximization over Matroids
[
Paper PDF]
Spotlight
Thu Jul 21 11:10 AM -- 11:15 AM (PDT) @ Room 327 - 329
Direct Behavior Specification via Constrained Reinforcement Learning
Spotlight
Thu Jul 21 11:10 AM -- 11:15 AM (PDT) @ Room 301 - 303
Model Selection in Batch Policy Optimization
Oral
Thu Jul 21 11:15 AM -- 11:35 AM (PDT) @ Room 327 - 329
Large Batch Experience Replay
Oral
Thu Jul 21 11:15 AM -- 11:35 AM (PDT) @ Room 301 - 303 None
Adversarially Trained Actor Critic for Offline Reinforcement Learning
Spotlight
Thu Jul 21 11:25 AM -- 11:30 AM (PDT) @ Hall F
Fast Population-Based Reinforcement Learning on a Single Machine
Spotlight
Thu Jul 21 11:30 AM -- 11:35 AM (PDT) @ Room 318 - 320
The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks
Spotlight
Thu Jul 21 11:35 AM -- 11:40 AM (PDT) @ Room 318 - 320
Instance Dependent Regret Analysis of Kernelized Bandits
Spotlight
Thu Jul 21 11:35 AM -- 11:40 AM (PDT) @ Room 327 - 329
Evolving Curricula with Regret-Based Environment Design
Spotlight
Thu Jul 21 11:35 AM -- 11:40 AM (PDT) @ Room 301 - 303
Optimal Estimation of Policy Gradient via Double Fitted Iteration
Spotlight
Thu Jul 21 11:40 AM -- 11:45 AM (PDT) @ Room 318 - 320
EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning
[
Paper PDF]
Spotlight
Thu Jul 21 11:40 AM -- 11:45 AM (PDT) @ Room 327 - 329
Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum
Spotlight
Thu Jul 21 11:40 AM -- 11:45 AM (PDT) @ Room 301 - 303
Provably Efficient Offline Reinforcement Learning for Partially Observable Markov Decision Processes
Spotlight
Thu Jul 21 11:45 AM -- 11:50 AM (PDT) @ Room 318 - 320
Tell me why! Explanations support learning relational and causal structure
Spotlight
Thu Jul 21 11:45 AM -- 11:50 AM (PDT) @ Room 327 - 329
Transformers are Meta-Reinforcement Learners
Spotlight
Thu Jul 21 11:45 AM -- 11:50 AM (PDT) @ Room 301 - 303
Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory
Spotlight
Thu Jul 21 11:45 AM -- 11:50 AM (PDT) @ Hall G
Proving Theorems using Incremental Learning and Hindsight Experience Replay
In
Applications
Spotlight
Thu Jul 21 11:50 AM -- 11:55 AM (PDT) @ Room 327 - 329
Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks
[
Paper PDF]
Spotlight
Thu Jul 21 11:50 AM -- 11:55 AM (PDT) @ Room 318 - 320
Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics
Spotlight
Thu Jul 21 11:50 AM -- 11:55 AM (PDT) @ Room 301 - 303
Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)
[
Paper PDF]
Spotlight
Thu Jul 21 11:50 AM -- 11:55 AM (PDT) @ Hall G
Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning
In
Applications
Spotlight
Thu Jul 21 11:55 AM -- 12:00 PM (PDT) @ Room 327 - 329
Constrained Variational Policy Optimization for Safe Reinforcement Learning
Spotlight
Thu Jul 21 11:55 AM -- 12:00 PM (PDT) @ Room 301 - 303
On the Role of Discount Factor in Offline Reinforcement Learning
Oral
Thu Jul 21 12:30 PM -- 12:50 PM (PDT) @ Room 309
From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses
Session
Thu Jul 21 12:30 PM -- 02:00 PM (PDT) @ Room 307 None
Optimization/Reinforcement Learning
Session
Thu Jul 21 12:30 PM -- 02:00 PM (PDT) @ Room 309 None
Reinforcement Learning/Optimization
Spotlight
Thu Jul 21 12:30 PM -- 12:35 PM (PDT) @ Room 307
Learning to Cut by Looking Ahead: Cutting Plane Selection via Imitation Learning
Spotlight
Thu Jul 21 12:35 PM -- 12:40 PM (PDT) @ Room 307
A Regret Minimization Approach to Multi-Agent Control
Spotlight
Thu Jul 21 12:40 PM -- 12:45 PM (PDT) @ Room 307
Multi-slots Online Matching with High Entropy
Spotlight
Thu Jul 21 12:45 PM -- 12:50 PM (PDT) @ Ballroom 3 & 4
Contextual Information-Directed Sampling
Spotlight
Thu Jul 21 12:45 PM -- 12:50 PM (PDT) @ Room 307
Decision-Focused Learning: Through the Lens of Learning to Rank
Spotlight
Thu Jul 21 12:50 PM -- 12:55 PM (PDT) @ Room 309
Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error
Spotlight
Thu Jul 21 12:50 PM -- 12:55 PM (PDT) @ Room 307
On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces
Spotlight
Thu Jul 21 12:55 PM -- 01:00 PM (PDT) @ Room 309
EqR: Equivariant Representations for Data-Efficient Reinforcement Learning
[
Paper PDF]
Spotlight
Thu Jul 21 12:55 PM -- 01:00 PM (PDT) @ Room 307
Asking for Knowledge (AFK): Training RL Agents to Query External Knowledge Using Language
Spotlight
Thu Jul 21 01:00 PM -- 01:05 PM (PDT) @ Room 309
Imitation Learning by Estimating Expertise of Demonstrators
[
Paper PDF]
Spotlight
Thu Jul 21 01:00 PM -- 01:05 PM (PDT) @ Room 307
Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning
Oral
Thu Jul 21 01:05 PM -- 01:25 PM (PDT) @ Room 307
An Analytical Update Rule for General Policy Optimization
Spotlight
Thu Jul 21 01:05 PM -- 01:10 PM (PDT) @ Room 309
Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments
Spotlight
Thu Jul 21 01:10 PM -- 01:15 PM (PDT) @ Room 309
Off-Policy Evaluation for Large Action Spaces via Embeddings
Oral
Thu Jul 21 01:15 PM -- 01:35 PM (PDT) @ Room 309
Online Decision Transformer
Spotlight
Thu Jul 21 01:25 PM -- 01:30 PM (PDT) @ Room 327 - 329
Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning approach
Spotlight
Thu Jul 21 01:25 PM -- 01:30 PM (PDT) @ Room 307
Making Linear MDPs Practical via Contrastive Representation Learning
Spotlight
Thu Jul 21 01:30 PM -- 01:35 PM (PDT) @ Room 307
Flow-based Recurrent Belief State Learning for POMDPs
Spotlight
Thu Jul 21 01:30 PM -- 01:35 PM (PDT) @ Ballroom 1 & 2
Flowformer: Linearizing Transformers with Conservation Flows
Spotlight
Thu Jul 21 01:35 PM -- 01:40 PM (PDT) @ Room 309
Learning-based Optimisation of Particle Accelerators Under Partial Observability Without Real-World Training
Spotlight
Thu Jul 21 01:35 PM -- 01:40 PM (PDT) @ Room 327 - 329
On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning
Spotlight
Thu Jul 21 01:35 PM -- 01:40 PM (PDT) @ Room 307
A Parametric Class of Approximate Gradient Updates for Policy Optimization
Spotlight
Thu Jul 21 01:40 PM -- 01:45 PM (PDT) @ Room 309
How to Leverage Unlabeled Data in Offline Reinforcement Learning
Spotlight
Thu Jul 21 01:40 PM -- 01:45 PM (PDT) @ Room 327 - 329
Utility Theory for Sequential Decision Making
Spotlight
Thu Jul 21 01:40 PM -- 01:45 PM (PDT) @ Room 307
Retrieval-Augmented Reinforcement Learning
Spotlight
Thu Jul 21 01:45 PM -- 01:50 PM (PDT) @ Room 309
Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning
Spotlight
Thu Jul 21 01:45 PM -- 01:50 PM (PDT) @ Room 307
Robust Policy Learning over Multiple Uncertainty Sets
Spotlight
Thu Jul 21 01:50 PM -- 01:55 PM (PDT) @ Room 309
Lightweight Projective Derivative Codes for Compressed Asynchronous Gradient Descent
Spotlight
Thu Jul 21 01:50 PM -- 01:55 PM (PDT) @ Room 307
Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL
[
Paper PDF]
Spotlight
Thu Jul 21 01:55 PM -- 02:00 PM (PDT) @ Room 309
Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data
Spotlight
Thu Jul 21 01:55 PM -- 02:00 PM (PDT) @ Room 307
Learning Dynamics and Generalization in Deep Reinforcement Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #123
Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning
[
Paper PDF]
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #119
Do Differentiable Simulators Give Better Policy Gradients?
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #109
Proving Theorems using Incremental Learning and Hindsight Experience Replay
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #107
Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #308
Neuro-Symbolic Hierarchical Rule Induction
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #412
Toward Compositional Generalization in Object-Oriented World Modeling
[
Paper PDF]
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #414
Fast Population-Based Reinforcement Learning on a Single Machine
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #423
Flowformer: Linearizing Transformers with Conservation Flows
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #604
Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #838
The Importance of Non-Markovianity in Maximum State Entropy Exploration
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #837
Continuous Control with Action Quantization from Demonstrations
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #829
Balancing Sample Efficiency and Suboptimality in Inverse Reinforcement Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #823
Interactive Inverse Reinforcement Learning for Cooperative Games
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #821
A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #817
Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #809
A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #805
Learning Stochastic Shortest Path with Linear Function Approximation
[
Paper PDF]
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #801
Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #902
Learning Bellman Complete Representations for Offline Policy Evaluation
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #906
A Simple Reward-free Approach to Constrained Reinforcement Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #908
Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #914
Adversarially Trained Actor Critic for Offline Reinforcement Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #918
Provably Efficient Offline Reinforcement Learning for Partially Observable Markov Decision Processes
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #920
Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory
[
Paper PDF]
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #924
On the Role of Discount Factor in Offline Reinforcement Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #926
EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #930
Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #932
Generalised Policy Improvement with Geometric Policy Composition
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #934
Offline Meta-Reinforcement Learning with Online Self-Supervision
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #936
Divergence-Regularized Multi-Agent Actor-Critic
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #929
Understanding Policy Gradient Algorithms: A Sensitivity-Based Approach
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #927
Off-Policy Reinforcement Learning with Delayed Rewards
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #923
Direct Behavior Specification via Constrained Reinforcement Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #921
Large Batch Experience Replay
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #919
Evolving Curricula with Regret-Based Environment Design
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #915
Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #913
Transformers are Meta-Reinforcement Learners
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #911
Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #909
Constrained Variational Policy Optimization for Safe Reinforcement Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #907
On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #905
Asking for Knowledge (AFK): Training RL Agents to Query External Knowledge Using Language
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #903
Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning
[
Paper PDF]
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1002
An Analytical Update Rule for General Policy Optimization
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1010
Retrieval-Augmented Reinforcement Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1012
Robust Policy Learning over Multiple Uncertainty Sets
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1014
Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1018
Learning Dynamics and Generalization in Deep Reinforcement Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1020
From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1026
EqR: Equivariant Representations for Data-Efficient Reinforcement Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1027
Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1023
Online Decision Transformer
[
Paper PDF]
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1021
Learning-based Optimisation of Particle Accelerators Under Partial Observability Without Real-World Training
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1019
How to Leverage Unlabeled Data in Offline Reinforcement Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1017
Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1124
First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1123
Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1121
Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1117
Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1111
Branching Reinforcement Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1101
Federated Reinforcement Learning: Linear Speedup Under Markovian Sampling
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1318
Contextual Information-Directed Sampling
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1413
Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning approach
[
Paper PDF]
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1422
On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning
Poster
Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1424
Utility Theory for Sequential Decision Making
[
Paper PDF]
Workshop
Fri Jul 22 05:45 AM -- 03:30 PM (PDT) @ Room 321 - 323
ICML workshop on Machine Learning for Cybersecurity (ICML-ML4Cyber)
Workshop
Fri Jul 22 06:00 AM -- 05:00 PM (PDT) @ Hall G None
Decision Awareness in Reinforcement Learning
Workshop
Sat Jul 23 05:45 AM -- 03:00 PM (PDT) @ Room 314 - 315
Complex feedback in online learning
Workshop
Sat Jul 23 06:00 AM -- 02:30 PM (PDT) @ Ballroom 1 None
Responsible Decision Making in Dynamic Environments
Workshop
Sat Jul 23 06:20 AM -- 02:45 PM (PDT) @ Room 308
Workshop on Distribution-Free Uncertainty Quantification