Offline RL

More for Less: Safe Policy Improvement with Stronger Performance Guarantees IJCAI 2023 MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning CoRL 2023 Multi-Horizon Learning in Procedurally-Generated Environments for Off-Policy Reinforcement Learning (Student Abstract) AAAI 2023 Multi-Task Off-Policy Learning from Bandit Feedback ICML 2023 Mutual Information Regularized Offline Reinforcement Learning NeurIPS 2023 Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game ICLR 2023 Nearly Optimal Latent State Decoding in Block MDPs AISTATS 2023 Neural Laplace Control for Continuous-time Delayed Systems AISTATS 2023 No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions NeurIPS 2023 Offline Imitation Learning with Variational Counterfactual Reasoning NeurIPS 2023 Offline Learning in Markov Games with General Function Approximation ICML 2023 Offline Meta Reinforcement Learning with In-Distribution Online Adaptation ICML 2023 Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage NeurIPS 2023 Offline Model-Based Reinforcement Learning for Tokamak Control L4DC 2023 Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization NeurIPS 2023 Offline Quantum Reinforcement Learning in a Conservative Manner AAAI 2023 Offline Reinforcement Learning for Mixture-of-Expert Dialogue Management NeurIPS 2023 Offline Reinforcement Learning with Closed-Form Policy Improvement Operators ICML 2023 Offline Reinforcement Learning with Differential Privacy NeurIPS 2023 Offline RL for Natural Language Generation with Implicit Language Q Learning ICLR 2023 Offline RL with Discrete Proxy Representations for Generalizability in POMDPs NeurIPS 2023 Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization ICLR 2023 Off-Policy Actor-Critic with Emphatic Weightings JMLR 2023 Off-Policy Evaluation for Human Feedback NeurIPS 2023 Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling ICML 2023