← Methods
Reinforcement Learning › Methods ›

Offline RL

725 directly classified papers

Papers per year

Papers

Minimax Regret for Stochastic Shortest Path with Adversarial Costs and Known Transition COLT 2021
A Workflow for Offline Model-Free Robotic Reinforcement Learning CORL 2021
Safe Driving via Expert Guided Policy Optimization CORL 2021
Learning Off-Policy with Online Planning CORL 2021
Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs NIPS 2021
Control Variates for Slate Off-Policy Evaluation NIPS 2021
Off-Policy Evaluation and Learning for External Validity under a Covariate Shift NIPS 2020
Q* Approximation Schemes for Batch Reinforcement Learning: A Theoretical Comparison UAI 2020
Private Reinforcement Learning with PAC and Regret Guarantees ICML 2020
Minimax Weight and Q-Function Learning for Off-Policy Evaluation ICML 2020
Counterfactual Data Augmentation using Locally Factored Dynamics NIPS 2020
Multi-task Batch Reinforcement Learning with Metric Learning NIPS 2020
RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning NIPS 2020
Critic Regularized Regression NIPS 2020
Off-Policy Interval Estimation with Lipschitz Value Iteration NIPS 2020
Finite-Sample Analysis of Contractive Stochastic Approximation Using Smooth Convex Envelopes NIPS 2020
Offline Imitation Learning with a Misspecified Simulator NIPS 2020
CoinDICE: Off-Policy Confidence Interval Estimation NIPS 2020
Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies NIPS 2020
Provably Efficient Neural GTD for Off-Policy Learning NIPS 2020
Off-Policy Imitation Learning from Observations NIPS 2020
A Maximum-Entropy Approach to Off-Policy Evaluation in Average-Reward MDPs NIPS 2020
Self-Imitation Learning via Generalized Lower Bound Q-learning NIPS 2020
MOPO: Model-based Offline Policy Optimization NIPS 2020
BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning NIPS 2020