arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.07412cs.LGcs.AI
收藏

基于转移距离表示学习的辅助奖励生成

Auxiliary Reward Generation with Transition Distance Representation Learning

Harbin Institute of Technology(哈尔滨工业大学);Harbin Engineering University(哈尔滨工程大学);CALT(中国运载火箭技术研究院)

Siyuan Li, Shijie Han, Yingnan Zhao, By Liang, Peng Liu

AI总结:

针对强化学习中人工奖励设计费力且易受认知偏差影响的问题,提出基于转移距离表示学习的辅助奖励生成方法,无需人类知识即可在单任务和技能链接场景中自动生成辅助奖励,有效提升学习效率与收敛稳定性。

摘要:

强化学习(RL)在具有挑战性的序列决策问题中展现了其优势。RL中的奖励函数对学习性能至关重要,因为它作为任务完成程度的衡量标准。在现实问题中,奖励主要由人工设计,需要费力的调整,且容易受到人类认知偏差的影响。为实现自动辅助奖励生成,我们提出了一种新颖的表示学习方法,能够衡量状态间的“转移距离”。基于这些表示,我们引入了一种辅助奖励生成技术,适用于单任务和技能链接场景,无需人类知识。所提方法在广泛的操作任务中进行了评估。实验结果证明了衡量状态间转移距离的有效性以及辅助奖励带来的提升,不仅促进了更好的学习效率,还增加了收敛稳定性。

英文摘要:

Reinforcement learning (RL) has shown its strength in challenging sequential decision-making problems. The reward function in RL is crucial to the learning performance, as it serves as a measure of the task completion degree. In real-world problems, the rewards are predominantly human-designed, which requires laborious tuning, and is easily affected by human cognitive biases. To achieve automatic auxiliary reward generation, we propose a novel representation learning approach that can measure the ``transition distance'' between states. Building upon these representations, we introduce an auxiliary reward generation technique for both single-task and skill-chaining scenarios without the need for human knowledge. The proposed approach is evaluated in a wide range of manipulation tasks. The experiment results demonstrate the effectiveness of measuring the transition distance between states and the induced improvement by auxiliary rewards, which not only promotes better learning efficiency but also increases convergent stability.

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。

↑