Temporally extended successor feature neural episodic control

Author:

Zhu Xianchao

Abstract

AbstractOne of the long-term goals of reinforcement learning is to build intelligent agents capable of rapidly learning and flexibly transferring skills, similar to humans and animals. In this paper, we introduce an episodic control framework based on the temporal expansion of subsequent features to achieve these goals, which we refer to as Temporally Extended Successor Feature Neural Episodic Control (TESFNEC). This method has shown impressive results in significantly improving sample efficiency and elegantly reusing previously learned strategies. Crucially, this model enhances agent training by incorporating episodic memory, significantly reducing the number of iterations required to learn the optimal policy. Furthermore, we adopt the temporal expansion of successor features a technique to capture the expected state transition dynamics of actions. This form of temporal abstraction does not entail learning a top-down hierarchy of task structures but focuses on the bottom-up combination of actions and action repetitions. Thus, our approach directly considers the temporal scope of sequences of temporally extended actions without requiring predefined or domain-specific options. Experimental results in the two-dimensional object collection environment demonstrate that the method proposed in this paper optimizes learning policies faster than baseline reinforcement learning approaches, leading to higher average returns.

Funder

Research Foundation for Advanced Talents of Henan University of Technology

Key Scientific Research Projects of Higher Education Institutions in Henan Province

Key Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education

Publisher

Springer Science and Business Media LLC

Reference70 articles.

1. Littman, M. L. Reinforcement learning improves behaviour from evaluative feedback. Nature 521(7553), 445 (2015).

2. Sutton, R. S. & Barto, A. G. Reinforcement Learning: An Introduction (MIT Press, 2018).

3. Tenenbaum, J. B., Kemp, C., Griffiths, T. L. & Goodman, N. D. How to grow a mind: Statistics, structure, and abstraction. Science 331(6022), 1279–1285 (2011).

4. Metelli, A. M., Mazzolini, F., Bisi, L., Sabbioni, L. & Restelli, M. Control frequency adaptation via action persistence in batch reinforcement learning. In International Conference on Machine Learning, PMLR 6862–6873 (2020).

5. Silver, D. et al. Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016).

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3