Offline RL

Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning ICML 2021 S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning in Robotics CoRL 2021 Safe Driving via Expert Guided Policy Optimization CoRL 2021 Scalable Bayesian Inverse Reinforcement Learning ICLR 2021 Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement Learning ICML 2021 SOPE: Spectrum of Off-Policy Estimators NeurIPS 2021 Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient ICML 2021 State Relevance for Off-Policy Evaluation ICML 2021 Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret NeurIPS 2021 Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning NeurIPS 2021 The Difficulty of Passive Learning in Deep Reinforcement Learning NeurIPS 2021 Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach EMNLP 2021 Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning NeurIPS 2021 Towards Instance-Optimal Offline Reinforcement Learning with Pessimism NeurIPS 2021 Towards Real Robot Learning in the Wild: A Case Study in Bipedal Locomotion CoRL 2021 Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble NeurIPS 2021 Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning ICML 2021 Understanding the World Through Action CoRL 2021 Variance-Aware Off-Policy Evaluation with Linear Function Approximation NeurIPS 2021 Weighted model estimation for offline model-based reinforcement learning NeurIPS 2021 What are the Statistical Limits of Offline RL with Linear Function Approximation? ICLR 2021 What Matters in Learning from Offline Human Demonstrations for Robot Manipulation CoRL 2021 You Only Evaluate Once: a Simple Baseline Algorithm for Offline RL CoRL 2021 Accountable Off-Policy Evaluation With Kernel Bellman Statistics ICML 2020 Adaptive Estimator Selection for Off-Policy Evaluation ICML 2020