Reinforcement Learning

Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning NAACL 2025 IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic ICML 2025 Image Difference Captioning via Adversarial Preference Optimization EMNLP 2025 Imagination-Limited Q-Learning for Offline Reinforcement Learning IJCAI 2025 Imitation Learning Backoff: Reinforcement Learning-based Channel Access for Guaranteeing Fairness (Student Abstract) AAAI 2025 Imitation Learning Based on Disentangled Representation Learning of Behavioral Characteristics CoRL 2025 Imitation Learning from a Single Temporally Misaligned Video ICML 2025 Imitation Learning via Focused Satisficing IJCAI 2025 IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation RSS 2025 Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions IJCAI 2025 Implicit Neural-Representation Learning for Elastic Deformable-Object Manipulations RSS 2025 Improved Lower Bounds for First-order Stochastic Non-convex Optimization under Markov Sampling ICML 2025 Improved Offline Contextual Bandits with Second-Order Bounds: Betting and Freezing COLT 2025 Improved Off-policy Reinforcement Learning in Biological Sequence Design ICML 2025 Improved Online Confidence Bounds for Multinomial Logistic Bandits ICML 2025 Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance ICML 2025 Improved Regret Bounds for Online Fair Division with Bandit Learning AAAI 2025 Improve Vision Language Model Chain-of-thought Reasoning ACL 2025 Improving Generalization in Offline Reinforcement Learning via Latent Distribution Representation Learning AAAI 2025 Improving Retrospective Language Agents via Joint Policy Gradient Optimization NAACL 2025 Improving Reward Model Generalization from Adversarial Process Enhanced Preferences ICML 2025 Improving the Continuity of Goal-Achievement Ability via Policy Self-Regularization for Goal-Conditioned Reinforcement Learning ICML 2025 Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning EMNLP 2025 Improving Transformer World Models for Data-Efficient RL ICML 2025 Improving Value Estimation Critically Enhances Vanilla Policy Gradient ICML 2025