arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.02481cs.LGcs.AI
收藏

面向深度强化学习的基于任务相关性的近端发展区课程设计

Proximal Curriculum with Task Correlations for Deep Reinforcement Learning

Max Planck Institute for Software Systems(马克斯·普朗克软件系统研究所);The Alan Turing Institute(艾伦·图灵研究所)

Georgios Tzannetos, Parameswaran Kamalaruban, Adish Singla

AI总结:

本文提出 ProCuRL-Target 课程设计方法,利用任务相关性在上下文多任务强化学习中平衡任务难度与目标分布推进,并通过理论分析和多领域实验验证其加速深度 RL 训练的有效性。

摘要:

强化学习(RL)的课程设计可以加快智能体的学习过程,并帮助其学会在复杂任务上表现良好。然而,现有技术通常需要针对特定领域进行超参数调优,涉及昂贵的任务选择优化过程,或者仅适用于特定的学习目标。在本工作中,我们考虑上下文多任务设置下的课程设计,其中智能体的最终性能是相对于复杂任务上的目标分布来衡量的。我们的课程设计基于“近端发展区”(Zone of Proximal Development)概念,该概念已被证明在加速 RL 智能体在所有任务均匀分布下的学习过程方面是有效的。我们提出了一种新颖的课程方法 ProCuRL-Target,该方法通过利用任务相关性,在为目标分布推进智能体学习的同时,有效平衡了选择对智能体而言难度适中的任务的需求。我们通过分析一个带有 REINFORCE 学习者模型的简单学习设置,从理论上论证了 ProCuRL-Target 的任务选择策略。我们在多个具有挑战性目标任务分布的领域中的实验结果表明,在加速深度 RL 智能体的训练过程方面,我们的课程策略优于最先进的基线方法。

英文摘要:

Curriculum design for reinforcement learning (RL) can speed up an agent's learning process and help it learn to perform well on complex tasks. However, existing techniques typically require domain-specific hyperparameter tuning, involve expensive optimization procedures for task selection, or are suitable only for specific learning objectives. In this work, we consider curriculum design in contextual multi-task settings where the agent's final performance is measured w.r.t. a target distribution over complex tasks. We base our curriculum design on the Zone of Proximal Development concept, which has proven to be effective in accelerating the learning process of RL agents for uniform distribution over all tasks. We propose a novel curriculum, ProCuRL-Target, that effectively balances the need for selecting tasks that are not too difficult for the agent while progressing the agent's learning toward the target distribution via leveraging task correlations. We theoretically justify the task selection strategy of ProCuRL-Target by analyzing a simple learning setting with REINFORCE learner model. Our experimental results across various domains with challenging target task distributions affirm the effectiveness of our curriculum strategy over state-of-the-art baselines in accelerating the training process of deep RL agents.

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。

↑