paper-with-me

Papers

Preference-Guided Reinforcement Learning for Efficient Exploration

2024-07-09 · GuoJian Wang, Faguo Wu, Xiao Zhang, Tianyuan Chen, Xuyang Chen, Lin Zhao

In this paper, we investigate preference-based reinforcement learning (PbRL) that allows reinforcement learning (RL) agents to learn from human feedback. This is particularly valuable when defining a fine-grain reward function is not feasible. However, this approach is inefficient and impractical for promoting deep exploration in hard-exploration tasks with long horizons and sparse rewards. To tackle this issue, we introduce LOPE: Learning Online with trajectory Preference guidancE, an end-to-end preference-guided RL framework that enhances exploration efficiency in hard-exploration tasks. Our intuition is that LOPE directly adjusts the focus of online exploration by considering human feedback as guidance, avoiding learning a separate reward model from preferences. Specifically, LOPE includes a two-step sequential policy optimization process consisting of trust-region-based policy improvement and preference guidance steps. We reformulate preference guidance as a novel trajectory-wise state marginal matching problem that minimizes the maximum mean discrepancy distance between the preferred trajectories and the learned policy. Furthermore, we provide a theoretical analysis to characterize the performance improvement bound and evaluate the LOPE's effectiveness. When assessed in various challenging hard-exploration environments, LOPE outperforms several state-of-the-art methods regarding convergence rate and overall performance. The code used in this study is available at \url{https://github.com/buaawgj/LOPE}.

📄 PDF Abstract BibTeX arXiv:2407.06503

Code (1)

buaawgj/lope 공식 구현 pytorch

Tasks

Efficient Explorationreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Sampling Efficient Deep Reinforcement Learning through Preference-Guided Stochastic Exploration

2022-06-20 · Wenhui Huang, Cong Zhang, Jingda Wu, Xiangkun He 외

Massive practical works addressed by Deep Q-network (DQN) algorithm have indicated that stochastic policy, despite its simplicity, is the most frequently used exploration approach. However, most existing stochastic explo…

Atari GamesDeep Reinforcement LearningQ-Learningreinforcement-learning+2

SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning

2025-06-17 · Hexian Ni, Tao Lu, Haoyuan Hu, Yinghao Cai 외

Preference-based Reinforcement Learning (PbRL) methods provide a solution to avoid reward engineering by learning reward models based on human preferences. However, poor feedback- and sample- efficiency still remain the …

Density EstimationRobot Manipulation

PrefPoE: Advantage-Guided Preference Fusion for Learning Where to Explore

2025-11-11 · Zhihao Lin, Lin Wu, Zhen Tian, Jianglin Lan arxiv

Exploration in reinforcement learning remains a critical challenge, as naive entropy maximization often results in high variance and inefficient policy updates. We introduce \textbf{PrefPoE}, a novel \textit{Preference-P…

Reinforcement Learning

PGDQN: Preference-Guided Deep Q-Network

2023-10-03 · IEEE Transactions on Neural Networks and Learning Systems 2023 10 · Wenhui Huang, Cong Zhang, Jingda Wu, Xiangkun He 외

Stochastic exploration is the key to the success of the Deep Q-network (DQN) algorithm. However, most existing stochastic exploration approaches either explore actions heuristically regardless of their Q-values or couple…

Atari GamesBenchmarkingEfficient ExplorationQ-Learning+1

BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modeling

2026-03-01 · Jiachen Yang, Xianhui Lin, Yi Dong, Zebiao Zheng 외 arxiv

Face retouching requires removing subtle imperfections while preserving unique facial identity features, in order to enhance overall aesthetic appeal. However, existing methods suffer from a fundamental trade-off. Superv…

Reinforcement LearningImage Editing