arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.11812cs.LGcs.AIstat.ML
收藏

自步调深度强化学习

Self-Paced Deep Reinforcement Learning

Intelligent Autonomous Systems, Technische Universität Darmstadt(达姆施塔特工业大学智能自主系统(Intelligent Autonomous Systems, Technische Universität Darmstadt));Department of Electrical Engineering and Automation, Aalto University(阿尔托大学电气工程与自动化系(Department of Electrical Engineering and Automation, Aalto University))

Pascal Klink, Carlo D'Eramo, Jan Peters, Joni Pajarinen

摘要:

课程强化学习(CRL)通过在整个学习过程中将智能体暴露于一系列定制的任务来提高智能体的学习速度和稳定性。尽管取得了经验上的成功,但CRL中的一个悬而未决的问题是如何为给定的强化学习(RL)代理自动生成课程,避免手动设计。在本文中,我们提出了一个答案,通过解释课程生成的推理问题,在任务的分布逐步学习接近目标任务。这种方法导致自动课程生成,其速度由代理控制,具有坚实的理论动机,并且易于与深度RL算法集成。在所进行的实验中,使用所提出的算法生成的课程显着提高了几种环境和深度RL算法的学习性能,匹配或优于现有的最先进的CRL算法。

英文摘要:

Curriculum reinforcement learning (CRL) improves the learning speed and stability of an agent by exposing it to a tailored series of tasks throughout learning. Despite empirical successes, an open question in CRL is how to automatically generate a curriculum for a given reinforcement learning (RL) agent, avoiding manual design. In this paper, we propose an answer by interpreting the curriculum generation as an inference problem, where distributions over tasks are progressively learned to approach the target task. This approach leads to an automatic curriculum generation, whose pace is controlled by the agent, with solid theoretical motivation and easily integrated with deep RL algorithms. In the conducted experiments, the curricula generated with the proposed algorithm significantly improve learning performance across several environments and deep RL algorithms, matching or outperforming state-of-the-art existing CRL algorithms.

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。

↑