|
Poster
|
Tue 7:00
|
From Importance Sampling to Doubly Robust Policy Gradient
Jiawei Huang, Nan Jiang
|
|
|
Poster
|
Tue 8:00
|
GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values
Shangtong Zhang, Bo Liu, Shimon Whiteson
|
|
|
Poster
|
Tue 8:00
|
Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition
Chi Jin, Tiancheng Jin, Haipeng Luo, Suvrit Sra, Tiancheng Yu
|
|
|
Poster
|
Tue 10:00
|
Logarithmic Regret for Adversarial Online Control
Dylan Foster, Max Simchowitz
|
|
|
Poster
|
Tue 12:00
|
Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling
Yao Liu, Pierre-Luc Bacon, Emma Brunskill
|
|
|
Poster
|
Tue 13:00
|
Learning with Good Feature Representations in Bandits and in RL with a Generative Model
Tor Lattimore, Csaba Szepesvari, Gellért Weisz
|
|
|
Poster
|
Tue 14:00
|
Logarithmic Regret for Learning Linear Quadratic Regulators Efficiently
Asaf Cassel, Alon Cohen, Tomer Koren
|
|
|
Poster
|
Tue 15:00
|
Double Reinforcement Learning for Efficient and Robust Off-Policy Evaluation
Nathan Kallus, Masatoshi Uehara
|
|
|
Poster
|
Wed 5:00
|
Adaptive Estimator Selection for Off-Policy Evaluation
Yi Su, Pavithra Srinath, Akshay Krishnamurthy
|
|
|
Poster
|
Wed 9:00
|
Provable Self-Play Algorithms for Competitive Reinforcement Learning
Yu Bai, Chi Jin
|
|
|
Poster
|
Wed 10:00
|
Provable Representation Learning for Imitation Learning via Bi-level Optimization
Sanjeev Arora, Simon Du, Sham Kakade, Yuping Luo, Nikunj Saunshi
|
|
|
Poster
|
Wed 11:00
|
Learning Near Optimal Policies with Low Inherent Bellman Error
Andrea Zanette, Alessandro Lazaric, Mykel Kochenderfer, Emma Brunskill
|
|
|
Poster
|
Wed 14:00
|
Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes
Chen-Yu Wei, Mehdi Jafarnia, Haipeng Luo, Hiteshi Sharma, Rahul Jain
|
|
|
Poster
|
Wed 15:00
|
Statistically Efficient Off-Policy Policy Gradients
Nathan Kallus, Masatoshi Uehara
|
|
|
Poster
|
Thu 6:00
|
Reward-Free Exploration for Reinforcement Learning
Chi Jin, Akshay Krishnamurthy, Max Simchowitz, Tiancheng Yu
|
|
|
Poster
|
Thu 6:00
|
On the Expressivity of Neural Networks for Deep Reinforcement Learning
Kefan Dong, Yuping Luo, Tianhe (Kevin) Yu, Chelsea Finn, Tengyu Ma
|
|
|
Poster
|
Thu 7:00
|
Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound
Lin Yang, Mengdi Wang
|
|
|
Poster
|
Thu 7:00
|
Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning
Dipendra Kumar Misra, Mikael Henaff, Akshay Krishnamurthy, John Langford
|
|
|
Poster
|
Thu 7:00
|
Model-Based Reinforcement Learning with Value-Targeted Regression
Alex Ayoub, Zeyu Jia, Csaba Szepesvari, Mengdi Wang, Lin Yang
|
|
|
Poster
|
Thu 8:00
|
Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation
Shangtong Zhang, Bo Liu, Hengshuai Yao, Shimon Whiteson
|
|
|
Poster
|
Thu 9:00
|
On the Global Convergence Rates of Softmax Policy Gradient Methods
Jincheng Mei, Chenjun Xiao, Csaba Szepesvari, Dale Schuurmans
|
|
|
Poster
|
Thu 12:00
|
Naive Exploration is Optimal for Online LQR
Max Simchowitz, Dylan Foster
|
|
|
Poster
|
Thu 14:00
|
Optimistic Policy Optimization with Bandit Feedback
Lior Shani, Yonathan Efroni, Aviv Rosenberg, Shie Mannor
|
|
|
Poster
|
Thu 17:00
|
Minimax Weight and Q-Function Learning for Off-Policy Evaluation
Masatoshi Uehara, Jiawei Huang, Nan Jiang
|
|