policy optimization

Reward-Weighted Regression Converges to a Global Optimum AAAI 2022 Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum ICML 2022 Sample-Efficient Iterative Lower Bound Optimization of Deep Reactive Policies for Planning in Continuous MDPs AAAI 2022 Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic AAAI 2022 Sharp Analysis of Stochastic Optimization under Global Kurdyka-Lojasiewicz Inequality NeurIPS 2022 Socially-Attentive Policy Optimization in Multi-Agent Self-Driving System CoRL 2022 Supported Policy Optimization for Offline Reinforcement Learning NeurIPS 2022 The Geometry of Robust Value Functions ICML 2022 The Phenomenon of Policy Churn NeurIPS 2022 The Primacy Bias in Deep Reinforcement Learning ICML 2022 Towards painless policy optimization for constrained MDPs UAI 2022 Towards Safe Reinforcement Learning with a Safety Editor Policy NeurIPS 2022 Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translation EMNLP 2022 When to Update Your Model: Constrained Model-based Reinforcement Learning NeurIPS 2022 Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies ICML 2021 A Collaborative Multi-agent Reinforcement Learning Framework for Dialog Action Decomposition EMNLP 2021 Action redundancy in reinforcement learning UAI 2021 Active Offline Policy Selection NeurIPS 2021 Adversarial Policy Learning in Two-player Competitive Games ICML 2021 A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning ICML 2021 Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization ICLR 2021 Average-Reward Reinforcement Learning with Trust Region Methods IJCAI 2021 Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization ICML 2021 Boosting Offline Reinforcement Learning with Residual Generative Modeling IJCAI 2021 Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation COLT 2021