Reinforcement Learning

SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning ICLR 2025 Skill Disentanglement in Reproducing Kernel Hilbert Space AAAI 2025 SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback ICLR 2025 SMoSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks AAAI 2025 SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch AAAI 2025 SrSv: Integrating Sequential Rollouts with Sequential Value Estimation for Multi-agent Reinforcement Learning AAAI 2025 Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning ICLR 2025 StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization EMNLP 2025 Student-Informed Teacher Training ICLR 2025 SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement ACL 2025 Temporal Difference Learning: Why It Can Be Fast and How It Will Be Faster ICLR 2025 Towards Cost Sensitive Decision Making AISTATS 2025 Towards General-Purpose Model-Free Reinforcement Learning ICLR 2025 Trajectory-Class-Aware Multi-Agent Reinforcement Learning ICLR 2025 TreeRL: LLM Reinforcement Learning with On-Policy Tree Search ACL 2025 Truncated Gaussian Policy for Debiased Continuous Control AAAI 2025 Tunable LLM-based Proactive Recommendation Agent ACL 2025 Understanding Constraint Inference in Safety-Critical Inverse Reinforcement Learning ICLR 2025 Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning AAAI 2025 Unsupervised Zero-Shot Reinforcement Learning via Dual-Value Forward-Backward Representation ICLR 2025 UTILITY: Utilizing Explainable Reinforcement Learning to Improve Reinforcement Learning ICLR 2025 VerIF: Verification Engineering for Reinforcement Learning in Instruction Following EMNLP 2025 VLP: Vision-Language Preference Learning for Embodied Manipulation EMNLP 2025 VVC-Gym: A Fixed-Wing UAV Reinforcement Learning Environment for Multi-Goal Long-Horizon Problems ICLR 2025 WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning ICLR 2025