Methods

Offline stochastic shortest path: Learning, evaluation and towards optimality UAI 2022 Offline-to-Online Co-Evolutional User Simulator and Dialogue System EMNLP 2022 Off-Policy Evaluation for Action-Dependent Non-stationary Environments NeurIPS 2022 Off-Policy Evaluation for Episodic Partially Observable Markov Decision Processes under Non-Parametric Models NeurIPS 2022 Off-Policy Evaluation with Deficient Support Using Side Information NeurIPS 2022 Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory ICML 2022 Off-Policy Reinforcement Learning with Delayed Rewards ICML 2022 Off-Policy Risk Assessment for Markov Decision Processes AISTATS 2022 On Efficient Online Imitation Learning via Classification NeurIPS 2022 On Gap-dependent Bounds for Offline Reinforcement Learning NeurIPS 2022 On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning ICML 2022 On Instrumental Variable Regression for Deep Offline Policy Evaluation JMLR 2022 Online Ad Hoc Teamwork under Partial Observability ICLR 2022 Online Apprenticeship Learning AAAI 2022 Online Decision Transformer ICML 2022 Online Inverse Reinforcement Learning with Learned Observation Model CoRL 2022 Online Learning for Unknown Partially Observable MDPs AISTATS 2022 Online Reinforcement Learning for Mixed Policy Scopes NeurIPS 2022 On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning ICLR 2022 On-Policy Model Errors in Reinforcement Learning ICLR 2022 On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting NeurIPS 2022 On-Robot Learning With Equivariant Models CoRL 2022 On the Approximation of Cooperative Heterogeneous Multi-Agent Reinforcement Learning (MARL) using Mean Field Control (MFC) JMLR 2022 On the convergence of policy gradient methods to Nash equilibria in general stochastic games NeurIPS 2022 On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning ICLR 2022