Reinforcement Learning

The Accuracy Paradox in RLHF: When Better Reward Models Don’t Yield Better Language Models EMNLP 2024 The CoachAI Badminton Environment: A Novel Reinforcement Learning Environment with Realistic Opponents (Student Abstract) AAAI 2024 The CoachAI Badminton Environment: Bridging the Gap between a Reinforcement Learning Environment and Real-World Badminton Games AAAI 2024 The Dormant Neuron Phenomenon in Multi-Agent Reinforcement Learning Value Factorization NeurIPS 2024 The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning NeurIPS 2024 Theia: Distilling Diverse Vision Foundation Models for Robot Learning CoRL 2024 The Importance of Online Data: Understanding Preference Fine-tuning via Coverage NeurIPS 2024 The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space NeurIPS 2024 The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm ICML 2024 The Non-linear F-Design and Applications to Interactive Learning ICML 2024 The Power of Resets in Online Reinforcement Learning NeurIPS 2024 The surprising efficiency of temporal difference learning for rare event prediction NeurIPS 2024 The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning NeurIPS 2024 The Value of Reward Lookahead in Reinforcement Learning NeurIPS 2024 Think Before You Act: Decision Transformers with Working Memory ICML 2024 Tight Rates for Bandit Control Beyond Quadratics NeurIPS 2024 Tilde: Teleoperation for Dexterous In-Hand Manipulation Learning with a DeltaHand RSS 2024 Time-Constrained Robust MDPs NeurIPS 2024 Time-Efficient Reinforcement Learning with Stochastic Stateful Policies ICLR 2024 Timing as an Action: Learning When to Observe and Act AISTATS 2024 TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback ACL 2024 ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback EMNLP 2024 To Promote Full Cooperation in Social Dilemmas, Agents Need to Unlearn Loyalty IJCAI 2024 TorchRL: A data-driven decision-making library for PyTorch ICLR 2024 To the Max: Reinventing Reward in Reinforcement Learning ICML 2024