Policy Learning

VinePPO: Refining Credit Assignment in RL Training of LLMs ICML 2025 Vintix: Action Model via In-Context Reinforcement Learning ICML 2025 VIP: Vision Instructed Pre-training for Robotic Manipulation ICML 2025 VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms EMNLP 2025 ViUniT: Visual Unit Tests for More Robust Visual Programming CVPR 2025 VLP: Vision-Language Preference Learning for Embodied Manipulation EMNLP 2025 VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning CoRL 2025 Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings EMNLP 2025 Wasserstein Policy Optimization ICML 2025 “What are my options?"€: Explaining RL Agents with Diverse Near-Optimal Alternatives L4DC 2025 What Are Step-Level Reward Models Rewarding? Counterintuitive Findings from MCTS-Boosted Mathematical Reasoning AAAI 2025 When Maximum Entropy Misleads Policy Optimization ICML 2025 YESciEval: Robust LLM-as-a-Judge for Scientific Question Answering ACL 2025 Zero-Shot Action Generalization with Limited Observations AISTATS 2025 VITS : Variational Inference Thompson Sampling for contextual bandits ICML 2024 3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing CoRL 2024 A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective NeurIPS 2024 ABLE: Personalized Disability Support with Politeness and Empathy Integration EMNLP 2024 Absolute Policy Optimization: Enhancing Lower Probability Bound of Performance with High Confidence ICML 2024 Accelerated Policy Gradient for s-rectangular Robust MDPs with Large State Spaces ICML 2024 Accelerated Policy Gradient: On the Convergence Rates of the Nesterov Momentum for Reinforcement Learning ICML 2024 ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization ICML 2024 Achieving Õ(1/ε) Sample Complexity for Constrained Markov Decision Process NeurIPS 2024 A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learning IJCAI 2024 ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints ICML 2024