Automated curriculum learning for embodied agents a neuroevolutionary approach

Author:

Milano Nicola,Nolfi Stefano

Abstract

AbstractWe demonstrate how the evolutionary training of embodied agents can be extended with a curriculum learning algorithm that automatically selects the environmental conditions in which the evolving agents are evaluated. The environmental conditions are selected to adjust the level of difficulty to the ability level of the current evolving agents, and to challenge the weaknesses of the evolving agents. The method does not require domain knowledge and does not introduce additional hyperparameters. The results collected on two benchmark problems, that require to solve a task in significantly varying environmental conditions, demonstrate that the method proposed outperforms conventional learning methods and generates solutions which are robust to variations and able to cope with different environmental conditions.

Publisher

Springer Science and Business Media LLC

Subject

Multidisciplinary

Reference31 articles.

1. Lehman, J. & Miikkulainen, R. Neuroevolution. Schorpedia 8(6), 30977 (2013).

2. Harvey, I., Husbands, P. & Cliff, D. Seeing the light: artificial evolution, real vision. From Anim. Anim. 3, 392–401 (1994).

3. Gomez, F. & Miikkulainen, R. Incremental evolution of complex general behavior. Adapt. Behav. 5(3–4), 317–342 (1997).

4. Mouret, J. B. & Doncieux, S. Incremental evolution of animats’ behaviors as a multi-objective optimization. In International Conference on Simulation of Adaptive Behavior. 210–219. (Springer, Berlin, Heidelberg, 2008).

5. Narvekar, S. et al. Curriculum learning for reinforcement learning domains: a framework and survey. J. Mach. Learn. Res. 21(181), 1–50 (2020).

Cited by 6 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Interaction Rules Supporting Effective Flocking Behavior;Artificial Life;2024

2. Autoencoders as a Tool to Detect Nonlinear Relationships in Latent Variables Models;2023 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE);2023-10-25

3. Qualitative differences between evolutionary strategies and reinforcement learning methods for control of autonomous agents;Evolutionary Intelligence;2022-12-07

4. Progress and challenges in adaptive robotics;Frontiers in Robotics and AI;2022-10-24

5. Synaptic pruning with MAP-elites;Proceedings of the Genetic and Evolutionary Computation Conference Companion;2022-07-09

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