arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.06503cs.LG
收藏

偏好引导的强化学习用于高效探索

Preference-Guided Reinforcement Learning for Efficient Exploration

Guojian Wang, Jianxiang Liu, Xinyuan Li, Faguo Wu, Xiao Zhang, Tianyuan Chen, Xuyang Chen

AI总结:

本文提出LOPE框架,通过将人类偏好作为轨迹引导直接调整在线探索,避免学习单独奖励模型,并利用信赖域策略改进与状态边缘匹配优化,在困难探索任务中显著提升收敛速度与性能。

摘要:

本文研究了基于偏好的强化学习(PbRL),该方法使强化学习(RL)智能体能够从人类反馈中学习。当难以定义细粒度奖励函数时,这种方法尤其有价值。然而,在具有长时程和稀疏奖励的困难探索任务中,这种方法在促进深度探索方面效率低下且不切实际。为了解决这一问题,我们提出了LOPE:基于轨迹偏好引导的在线学习(Learning Online with trajectory Preference guidancE),这是一个端到端的偏好引导强化学习框架,旨在提高困难探索任务中的探索效率。我们的直觉是,LOPE通过将人类反馈视为引导,直接调整在线探索的焦点,从而避免从偏好中学习单独的奖励模型。具体而言,LOPE包含一种两步序列策略优化技术,该技术由基于信赖域的策略改进步骤和偏好引导步骤组成。我们将偏好引导重新表述为一个轨迹级状态边缘匹配问题,该问题最小化偏好轨迹与所学策略之间的最大均值差异距离。此外,我们提供了理论分析来刻画性能改进界限,并评估了LOPE的有效性。在各种具有挑战性的困难探索环境中进行评估时,LOPE在收敛速度和整体性能方面均优于多种最先进的方法。本研究使用的代码可在https://github.com/buaawgj/LOPE获取。

英文摘要:

In this paper, we investigate preference-based reinforcement learning (PbRL), which enables 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: \textbf{L}earning \textbf{O}nline with trajectory \textbf{P}reference guidanc\textbf{E}, 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, thereby avoiding the need to learn a separate reward model from preferences. Specifically, LOPE includes a two-step sequential policy optimization technique consisting of trust-region-based policy improvement and preference guidance steps. We reformulate preference guidance as a 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 effectiveness of the LOPE. When assessed in various challenging hard-exploration environments, LOPE outperforms several state-of-the-art methods in terms of convergence rate and overall performance.The code used in this study is available at https://github.com/buaawgj/LOPE.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑