Reinforcement Learning

On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation AAAI 2023 Online Adaptive Policy Selection in Time-Varying Systems: No-Regret via Contractive Perturbations NeurIPS 2023 Online Defense Strategies for Reinforcement Learning Against Adaptive Reward Poisoning AISTATS 2023 Online Learning with Off-Policy Feedback ALT 2023 Online Non-stochastic Control with Partial Feedback JMLR 2023 Online Nonstochastic Model-Free Reinforcement Learning NeurIPS 2023 Online Performative Gradient Descent for Learning Nash Equilibria in Decision-Dependent Games NeurIPS 2023 Online POMDP Planning with Anytime Deterministic Guarantees NeurIPS 2023 Online Reinforcement Learning in Stochastic Continuous-Time Systems COLT 2023 Online Reinforcement Learning with Uncertain Episode Lengths AAAI 2023 Online Tuning for Offline Decentralized Multi-Agent Reinforcement Learning AAAI 2023 On Many-Actions Policy Gradient ICML 2023 On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline ICML 2023 On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling and Beyond NeurIPS 2023 On the Challenges of Using Reinforcement Learning in Precision Drug Dosing: Delay and Prolongedness of Action Effects AAAI 2023 On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring COLT 2023 On the Convergence and Sample Complexity Analysis of Deep Q-Networks with ε-Greedy Exploration NeurIPS 2023 On The Convergence Of Policy Iteration-Based Reinforcement Learning With Monte Carlo Policy Evaluation AISTATS 2023 On the Convergence of SARSA with Linear Function Approximation ICML 2023 On the Data-Efficiency with Contrastive Image Transformation in Reinforcement Learning ICLR 2023 On the Effectiveness of Offline RL for Dialogue Response Generation ICML 2023 On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning ICLR 2023 On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization ICML 2023 On the Global Convergence of Risk-Averse Policy Gradient Methods with Expected Conditional Risk Measures ICML 2023 On the Importance of Exploration for Generalization in Reinforcement Learning NeurIPS 2023