← Methods
Reinforcement Learning › Methods ›

Offline RL

725 directly classified papers

Papers per year

Papers

Understanding the World Through Action CORL 2021
No-regret learning with high-probability in adversarial Markov decision processes UAI 2021
Fast Rates for the Regret of Offline Reinforcement Learning COLT 2021
Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm ICML 2021
On the Optimality of Batch Policy Optimization Algorithms ICML 2021
Optimal Off-Policy Evaluation from Multiple Logging Policies ICML 2021
Offline Reinforcement Learning from Human Feedback in Real-World Sequence-to-Sequence Tasks ACL 2021
IQ-Learn: Inverse soft-Q Learning for Imitation NIPS 2021
Towards Instance-Optimal Offline Reinforcement Learning with Pessimism NIPS 2021
Offline Meta Reinforcement Learning -- Identifiability Challenges and Effective Data Collection Strategies NIPS 2021
Offline RL Without Off-Policy Evaluation NIPS 2021
Curriculum Offline Imitating Learning NIPS 2021
Bellman-consistent Pessimism for Offline Reinforcement Learning NIPS 2021
Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret NIPS 2021
Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble NIPS 2021
Variance-Aware Off-Policy Evaluation with Linear Function Approximation NIPS 2021
Near-Optimal Offline Reinforcement Learning via Double Variance Reduction NIPS 2021
Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning NIPS 2021
Offline Model-based Adaptable Policy Learning NIPS 2021
Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning NIPS 2021
Continuous Doubly Constrained Batch Reinforcement Learning NIPS 2021
Conservative Data Sharing for Multi-Task Offline Reinforcement Learning NIPS 2021
Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism NIPS 2021
Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning NIPS 2021
Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings NIPS 2021