paper-with-me

홈 › Papers

UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning

2026-06-17 · Mohamed Nabail, Leo Kaixuan Cheng, Jingmin Wang, Nicholas Rhinehart arxiv

Preference-based RL provides an approach to learning reward models from pairwise comparisons of behaviors, bypassing the need for explicit reward design. However, existing methods typically rely on passive data collection and suffer from poor sample efficiency, especially during the early stages of learning. We introduce a model-based approach that actively directs exploration by jointly reasoning over uncertainties in the reward, dynamics, and value functions. Our method, Uncertainty-Balanced Preference Planning (UBP2), uses ensembles of reward, dynamics, and value function models to evaluate candidate trajectories according to a unified score that combines expected reward, terminal value, and epistemic uncertainty. Planning under this objective yields an explicit tradeoff between exploitation and information acquisition without requiring ad hoc exploration heuristics. Under standard regularity assumptions, we establish sublinear regret guarantees for both finite-horizon and infinite-horizon settings. Empirically, experiments on the Meta-World benchmark show UBP2 achieves substantially higher sample efficiency than model-free preference-based methods and non-optimistic model-based baselines.

📄 PDF Abstract BibTeX arXiv:2606.19328

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Mitigating Strategy Preference Bias in Emotional Support Conversation via Uncertainty Estimations

2025-09-16 · Yougen Zhou, Qin Chen, Ningning Zhou, Jie Zhou 외 arxiv

Emotional support conversation (ESC) aims to alleviate distress through empathetic dialogue, yet large language models (LLMs) face persistent challenges in delivering effective ESC due to low accuracy in strategy plannin…

Reinforcement Learning

Uncertainty-Penalized Direct Preference Optimization

2024-10-26 · Sam Houliston, Alizée Pace, Alexander Immer, Gunnar Rätsch

Aligning Large Language Models (LLMs) to human preferences in content, style, and presentation is challenging, in part because preferences are varied, context-dependent, and sometimes inherently ambiguous. While successf…

reinforcement-learningReinforcement Learning

AcCoRD: Evaluating User-Agent Collaboration Under Realistic User Preference Dynamics

2026-08-28 · Tejas Srinivasan, Shikib Mehri, Nandita Shankar Naik, Anirban Das 외 arxiv

User preferences in user-agent collaboration are rarely static and fully-specified upfront: preferences are formed, revealed, adjusted, and relaxed during interaction. Existing benchmarks for evaluating user-agent collab…

Reward Uncertainty for Exploration in Preference-based Reinforcement Learning

2022-05-24 · ICLR 2022 4 · Xinran Liang, Katherine Shu, Kimin Lee, Pieter Abbeel

Conveying complex objectives to reinforcement learning (RL) agents often requires meticulous reward engineering. Preference-based RL methods are able to learn a more flexible reward model based on human preferences by ac…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Robot Manipulation

Improving Safety Alignment via Balanced Direct Preference Optimization

2026-03-24 · Shiji Zhao, Mengyang Wang, Shukun Xiong, Fangzhou Chen 외 arxiv

With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from Human Feedback (RLHF) has been adopted …

Reinforcement Learning