← Methods
Reinforcement Learning › Methods ›

Offline RL

725 directly classified papers

Papers per year

Papers

Instabilities of Offline RL with Pre-Trained Neural Representation ICML 2021
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning ICML 2021
Data-efficient Hindsight Off-policy Option Learning ICML 2021
Deep Reinforcement Learning amidst Continual Structured Non-Stationarity ICML 2021
Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality ICML 2021
Representation Matters: Offline Pretraining for Sequential Decision Making ICML 2021
Near Optimal Reward-Free Reinforcement Learning ICML 2021
Average-Reward Off-Policy Policy Evaluation with Function Approximation ICML 2021
A General Offline Reinforcement Learning Framework for Interactive Recommendation AAAI 2021
Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach EMNLP 2021
Online Sparse Reinforcement Learning AISTATS 2021
Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning AISTATS 2021
Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders AISTATS 2021
Non-Stationary Off-Policy Optimization AISTATS 2021
Finite-Sample Regret Bound for Distributionally Robust Offline Tabular Reinforcement Learning AISTATS 2021
Offline Contextual Bandits with Overparameterized Models ICML 2021
BRAC+: Improved Behavior Regularized Actor Critic for Offline Reinforcement Learning ACML 2021
Offline Reinforcement Learning from Images with Latent Space Models L4DC 2021
S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning in Robotics CORL 2021
Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation CORL 2021
Dealing with the Unknown: Pessimistic Offline Reinforcement Learning CORL 2021
Towards Real Robot Learning in the Wild: A Case Study in Bipedal Locomotion CORL 2021
You Only Evaluate Once: a Simple Baseline Algorithm for Offline RL CORL 2021
What Matters in Learning from Offline Human Demonstrations for Robot Manipulation CORL 2021
Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble CORL 2021