Reinforcement Learning

Off-Policy Risk Assessment for Markov Decision Processes AISTATS 2022 On Instrumental Variable Regression for Deep Offline Policy Evaluation JMLR 2022 Online Apprenticeship Learning AAAI 2022 Online Decision Transformer ICML 2022 Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs ICLR 2022 On the convergence of policy gradient methods to Nash equilibria in general stochastic games NeurIPS 2022 On the Convergence Rate of Off-Policy Policy Optimization Methods with Density-Ratio Correction AISTATS 2022 On the Global Optimum Convergence of Momentum-based Policy Gradient AISTATS 2022 On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL NeurIPS 2022 Operator Splitting Value Iteration NeurIPS 2022 Optimal and instance-dependent guarantees for Markovian linear stochastic approximation COLT 2022 Optimal Estimation of Policy Gradient via Double Fitted Iteration ICML 2022 PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation ICML 2022 Partner Personas Generation for Dialogue Response Generation NAACL 2022 Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity ICML 2022 Planning with Participation Constraints AAAI 2022 Policy Gradient With Serial Markov Chain Reasoning NeurIPS 2022 Policy Learning and Evaluation with Randomized Quasi-Monte Carlo AISTATS 2022 Policy Optimization for Stochastic Shortest Path COLT 2022 Polynomial Time Reinforcement Learning in Factored State MDPs with Linear Value Functions AISTATS 2022 PowerGym: A Reinforcement Learning Environment for Volt-Var Control in Power Distribution Systems L4DC 2022 PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS Decoding NAACL 2022 Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environments NeurIPS 2022 Preference Exploration for Efficient Bayesian Optimization with Multiple Outcomes AISTATS 2022 Pre-Trained Language Models for Interactive Decision-Making NeurIPS 2022