arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.01620cs.LGcs.AIstat.ML
收藏

时间约束下多任务强化学习的最优选择

Optimal Options for Multi-Task Reinforcement Learning Under Time Constraints

University of Rome ‘Sapienza’(罗马第一大学(Sapienza大学));Federal University of Rio Grande do Sul (UFRGS)(南里奥格兰德联邦大学(UFRGS));National Research Council of Italy (CNR)(意大利国家研究委员会(CNR))

Manuel Del Verme, Bruno Castro da Silva, Gianluca Baldassarre

摘要:

强化学习可以极大地受益于使用选项作为编码重复行为和促进探索的一种方式。一个重要的开放问题是如何能够自主学习有用的选项时,解决相关任务的特定分布的代理。我们调查的一些条件,影响最优的选项,在设置代理人有一个有限的时间预算学习每个任务和任务分配可能涉及不同程度的相似性的问题。我们直接搜索最优的选项集,发现的选项显着不同的因素,如可用的学习时间预算和发现的选项优于流行的选项生成算法。

英文摘要:

Reinforcement learning can greatly benefit from the use of options as a way of encoding recurring behaviours and to foster exploration. An important open problem is how can an agent autonomously learn useful options when solving particular distributions of related tasks. We investigate some of the conditions that influence optimality of options, in settings where agents have a limited time budget for learning each task and the task distribution might involve problems with different levels of similarity. We directly search for optimal option sets and show that the discovered options significantly differ depending on factors such as the available learning time budget and that the found options outperform popular option-generation heuristics.

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。

↑