Reinforcement Learning

Offline Model-Based Optimization via Policy-Guided Gradient Search AAAI 2024 On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization EMNLP 2024 Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement Learning EMNLP 2024 PACE: Improving Prompt with Actor-Critic Editing for Large Language Model ACL 2024 Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning NeurIPS 2024 Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning ICLR 2024 PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation NeurIPS 2024 PMAC: Personalized Multi-Agent Communication AAAI 2024 Policy-shaped prediction: avoiding distractions in model-based reinforcement learning NeurIPS 2024 PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models CVPR 2024 PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference NeurIPS 2024 Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences CVPR 2024 Prompt-Based Length Controlled Generation with Multiple Control Types ACL 2024 Proofread: Fixes All Errors with One Tap ACL 2024 Pure-Past Action Masking AAAI 2024 Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation NeurIPS 2024 Real-Time Recurrent Learning using Trace Units in Reinforcement Learning NeurIPS 2024 REBEL: Reinforcement Learning via Regressing Relative Rewards NeurIPS 2024 ReCoRe: Regularized Contrastive Representation Learning of World Model CVPR 2024 Recursive Introspection: Teaching Language Model Agents How to Self-Improve NeurIPS 2024 Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs NeurIPS 2024 Reinforcement Learning-Driven LLM Agent for Automated Attacks on LLMs ACL 2024 Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers NeurIPS 2024 RePALM: Popular Quote Tweet Generation via Auto-Response Augmentation ACL 2024 ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search NeurIPS 2024