Reinforcement Learning

Robust Knowledge Transfer in Tiered Reinforcement Learning NeurIPS 2023 RPM: Generalizable Multi-Agent Policies for Multi-Agent Reinforcement Learning ICLR 2023 Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-Free RL ICLR 2023 Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms NeurIPS 2023 SafeLight: A Reinforcement Learning Method toward Collision-Free Traffic Signal Control AAAI 2023 Safe Policy Improvement for POMDPs via Finite-State Controllers AAAI 2023 Scalable Spatial Memory for Scene Rendering and Navigation AAAI 2023 Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning ICLR 2023 Self-Supervised Behavior Cloned Transformers are Path Crawlers for Text Games EMNLP 2023 Simple Emergent Action Representations from Multi-Task Policy Training ICLR 2023 Simultaneously Updating All Persistence Values in Reinforcement Learning AAAI 2023 SMART: Self-supervised Multi-task pretrAining with contRol Transformers ICLR 2023 State-Conditioned Adversarial Subgoal Generation AAAI 2023 State Regularized Policy Optimization on Data with Dynamics Shift NeurIPS 2023 Stay Moral and Explore: Learn to Behave Morally in Text-based Games ICLR 2023 STL-Based Synthesis of Feedback Controllers Using Reinforcement Learning AAAI 2023 Supervised Pretraining Can Learn In-Context Reinforcement Learning NeurIPS 2023 Supported Value Regularization for Offline Reinforcement Learning NeurIPS 2023 Systematic Rectification of Language Models via Dead-end Analysis ICLR 2023 The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types AAAI 2023 The In-Sample Softmax for Offline Reinforcement Learning ICLR 2023 The Sufficiency of Off-Policyness and Soft Clipping: PPO Is Still Insufficient according to an Off-Policy Measure AAAI 2023 Timing is Everything: Learning to Act Selectively with Costly Actions and Budgetary Constraints ICLR 2023 Towards Deployment-Efficient and Collision-Free Multi-Agent Path Finding (Student Abstract) AAAI 2023 Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Games ACML 2023