期刊
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
卷 21, 期 4, 页码 601-615出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TEVC.2017.2664665
关键词
Memetic automaton; multiagent systems (MASs); natural selection; reinforcement learning (RL); transfer learning (TL)
资金
- National Research Foundation Singapore under its Interactive Digital Media (IDM) Strategic Research Programme
In this paper, we present an evolutionary transfer reinforcement learning framework (eTL) for developing intelligent agents capable of adapting to the dynamic environment of multiagent systems (MASs). Specifically, we take inspiration from Darwin's theory of natural selection and Universal Darwinism as the principal driving forces that govern the evolutionary knowledge transfer process. The essential backbone of our proposed eTL comprises several meme-inspired evolutionary mechanisms, namely meme representation, meme expression, meme assimilation, meme internal evolution, and meme external evolution. Our proposed approach constructs social selection mechanisms that are modeled after the principles of human learning to identify appropriate interacting partners. eTL also models the intrinsic parallelism of natural evolution and errors that are introduced due to the physiological limits of the agents' ability to perceive differences, so as to generate growth and variation of knowledge that agents have of the world, thus exhibiting higher adaptivity capabilities on solving complex problems. To verify the efficacy of the proposed paradigm, comprehensive investigations of the proposed eTL against existing state-of-the-art TL methods in MAS, are conducted on the minefield navigation tasks platform and the Unreal Tournament 2004 first person shooter computer game, in which homogeneous and heterogeneous learning machines are considered.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据