Policy Learning

The POWER of Ikigai: Optimizing Life Fulfillment with an Integrated User Simulator and Adaptive Hobby Recommender AAAI 2025 The Role of Environment Access in Agnostic Reinforcement Learning (Extended Abstract) COLT 2025 Thinking Out Loud: Do Reasoning Models Know When They’re Right? EMNLP 2025 Through the Valley: Path to Effective Long CoT Training for Small Language Models EMNLP 2025 Token-level Proximal Policy Optimization for Query Generation EMNLP 2025 To Measure or Not: A Cost-Sensitive, Selective Measuring Environment for Agricultural Management Decisions with Reinforcement Learning AAAI 2025 Tool-as-Interface: Learning Robot Policies from Observing Human Tool Use CoRL 2025 Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization EMNLP 2025 TopoCut: Learning Multi-Step Cutting with Spectral Rewards and Discrete Diffusion Policies CoRL 2025 Towards A Better Initial Policy Model For Scalable Long-CoT Reinforcement Learning ACL 2025 Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration ACL 2025 Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning ICML 2025 Towards Medical Complex Reasoning with LLMs through Medical Verifiable Problems ACL 2025 Towards Theoretical Understanding of Sequential Decision Making with Preference Feedback ICML 2025 TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies ICLR 2025 Tracking The Best Expert Privately ICML 2025 T-REG: Preference Optimization with Token-Level Reward Regularization ACL 2025 Truncated Gaussian Policy for Debiased Continuous Control AAAI 2025 Trust-Region Twisted Policy Improvement ICML 2025 Two-Stage Feature Generation with Transformer and Reinforcement Learning IJCAI 2025 Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures CoRL 2025 Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning EMNLP 2025 UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping CVPR 2025 uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs ICLR 2025 Value-aligned Behavior Cloning for Offline Reinforcement Learning via Bi-level Optimization ICLR 2025