( events)   Timezone: »  
The 2021 schedule is still incomplete
Fri Jul 23 06:00 AM -- 10:00 PM (PDT)
Reinforcement Learning for Real Life
Yuxi Li · Minmin Chen · Omer Gottesman · Lihong Li · Zongqing Lu · Rupam Mahmood · Niranjani Prasad · Zhiwei (Tony) Qin · Csaba Szepesvari · Matthew Taylor

Reinforcement learning (RL) is a general learning, predicting, and decision making paradigm and applies broadly in many disciplines, including science, engineering and humanities. RL has seen prominent successes in many problems, such as games, robotics, recommender systems. However, applying RL in the real world remains challenging, and a natural question is:

Why isn’t RL used even more often and how can we improve this?

The main goals of the workshop are to: (1) identify key research problems that are critical for the success of real-world applications; (2) report progress on addressing these critical issues; and (3) have practitioners share their success stories of applying RL to real-world problems, and the insights gained from such applications.

We invite paper submissions successfully applying RL algorithms to real-life problems and/or addressing practically relevant RL issues. Our topics of interest are general, including (but not limited to): 1) practical RL algorithms, which covers all algorithmic challenges of RL, especially those that directly address challenges faced by real-world applications; 2) practical issues: generalization, sample efficiency, exploration, reward, scalability, model-based learning, prior knowledge, safety, accountability, interpretability, reproducibility, hyper-parameter tuning; and 3) applications.

We have 6 premier panel discussions and 70+ great papers/posters. Welcome!

Poster Session
RL Foundation Panel (Panel Discussion)
RL Explainability & Interpretability Panel (Panel Discussion)
RL + Robotics Panel (Panel Discussion)
RL + Recommender Systems Panel (Panel Discussion)
RL Research-to-RealLife Gap Panel (Panel Discussion)
RL + Operations Research Panel (Panel Discussion)
Poster Session
Workshop ends (Break)
Attend2Pack: Bin Packing through Deep Reinforcement Learning with Attention (Poster)
Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention (Poster)
Understanding the Generalization Gap in Visual Reinforcement Learning (Poster)
Robust Risk-Sensitive Reinforcement Learning Agents for Trading Markets (Poster)
ModelLight: Model-Based Meta-Reinforcement Learning for Traffic Signal Control (Poster)
Reinforcement Learning with Logical Action-Aware Features for Polymer Discovery (Poster)
Off-Policy Evaluation with General Logging Policies (Poster)
Is Bang-Bang Control All You Need? (Poster)
Objective Robustness in Deep Reinforcement Learning (Poster)
MobILE: Model-Based Imitation Learning From Observation Alone (Poster)
Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage (Poster)
Data-Pooling Reinforcement Learning for Personalized Healthcare Intervention (Poster)
Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer (Poster)
Avoiding Overfitting to the Importance Weights in Offline Policy Optimization (Poster)
Improving Human Decision-Making with Machine Learning (Poster)
The Reflective Explorer: Online Meta-Exploration from Offline Data in Visual Tasks with Sparse Rewards (Poster)
Deploying a Machine Learning System for COVID-19 Testing in Greece (Poster)
Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks (Poster)
Reward Shaping for User Satisfaction in a REINFORCE Recommender (Poster)
AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning (Poster)
Topological Experience Replay for Fast Q-Learning (Poster)
Learning a Markov Model for evaluating Soccer Decision Making (Poster)
IV-RL: Leveraging Target Uncertainty Estimation for Sample Efficiency in Deep Reinforcement Learning (Poster)
What Can I Do Here? Learning New Skills by Imagining Visual Affordances (Poster)
Offline Reinforcement Learning as Anti-Exploration (Poster)
Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learning (Poster)
Optimization of high precision manufacturing by Monte Carlo Tree Search (Poster)
De novo drug design using reinforcement learning with graph-based deep generative models (Poster)
Revisiting Design Choices in Offline Model Based Reinforcement Learning (Poster)
Efficient Exploration by HyperDQN in Deep Reinforcement Learning (Poster)
Multi-agent Deep Covering Option Discovery (Poster)
Hierarchical Multiple-Instance Data Classification with Costly Features (Poster)
Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks (Poster)
Representation Learning for Out-of-distribution Generalization in Downstream Tasks (Poster)
ReLMM: Practical RL for Learning Mobile Manipulation Skills Using Only Onboard Sensors (Poster)
Learning Space Partitions for Path Planning (Poster)
Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap (Poster)
Reinforcement Learning as One Big Sequence Modeling Problem (Poster)
Continual Meta Policy Search for Sequential Multi-Task Learning (Poster)
Learning to Represent State with Perceptual Schemata (Poster)
Deep Reinforcement Learning for 3D Furniture Layout in Indoor Graphic Scenes (Poster)
Corruption Robust Offline Reinforcement Learning (Poster)
Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research (Poster)
Reward-Free Attacks in Multi-Agent Reinforcement Learning (Poster)
Graph Neural Network Reinforcement Learning for Autonomous Mobility-on-Demand Systems (Poster)
Learning Vision-Guided Quadrupedal Locomotionwith Cross-Modal Transformers (Poster)
Disentangled Attention as Intrinsic Regularization for Bimanual Multi-Object Manipulation (Poster)
Coordinate-wise Control Variates for Deep Policy Gradients (Poster)
Automatic Risk Adaptation in Distributional Reinforcement Learning (Poster)
Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations (Poster)
OffWorld Gym: Open-Access Physical Robotics Environment for Real-World Reinforcement Learning Benchmark and Research (Poster)
Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model (Poster)
On the Difficulty of Generalizing Reinforcement Learning Framework for Combinatorial Optimization (Poster)
Contingency-Aware Influence Maximization: A Reinforcement Learning Approach (Poster)
Continuous Doubly Constrained Batch Reinforcement Learning (Poster)
Reinforcement Learning for (Mixed) Integer Programming: Smart Feasibility Pump (Poster)
Neural Rate Control for Video Encoding using Imitation Learning (Poster)
DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning (Poster)
RRL: Resnet as representation for Reinforcement Learning (Poster)
Automating Power Networks: Improving RL Agent Robustness with Adversarial Training (Poster)
Safe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action Spaces (Poster)
Optimizing Dynamic Treatment Regimes via Volatile Contextual Gaussian Process Bandits (Poster)
Constraints Penalized Q-Learning for Safe Offline Reinforcement Learning (Poster)
The MineRL Competitions at NeurIPS 2021 (Poster)
IGLU: Interactive Grounded Language Understanding in a Collaborative Environment (Poster)
Designing Online Advertisements via Bandit and Reinforcement Learning (Poster)
Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings (Poster)
Mind the Gap: Safely Bridging Offline and Online Reinforcement Learning (Poster)
Hierarchical Imitation Learning with Contextual Bandits for DynamicTreatment Regimes (Poster)
Reinforcement Learning Agent Training with Goals for Real World Tasks (Poster)
A Policy Efficient Reduction Approach to Convex Constrained Deep Reinforcement Learning (Poster)
Value-Based Deep Reinforcement Learning Requires Explicit Regularization (Poster)
Multi-Task Offline Reinforcement Learning with Conservative Data Sharing (Poster)
Decision Transformer: Reinforcement Learning via Sequence Modeling (Poster)
Designing Interpretable Approximations to Deep Reinforcement Learning (Poster)