Genetic Programming And Multi-agent Layered Learning By Reinforcements
Genetic Programming And Multi-agent Layered Learning By Reinforcements
复制标题
遗传编程和强化多智能体分层学习
DOI：
--
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
Steven M. Gustafson
中科院分区：
文献类型：
--
作者：
W. Hsu;Steven M. Gustafson
我们提出了一个适应的标准遗传程序（GP）分层分解，多智能体学习问题。为了分解一个需要多个代理合作的问题，我们使用团队目标函数来推导出一个更简单的中间目标函数，用于合作代理对。我们应用GP首先优化中间，然后优化团队目标函数，使用早期GP的最终种群作为下一个的初始种子种群。这种分层学习方法有助于发现可以重用的原始行为，并根据共享的团队目标适应复杂的目标。我们使用这种方法来发展代理发挥机器人足球（keep-away足球）的子问题。最后，我们展示了分层学习GP如何进化出比标准GP更好的代理，包括具有自动定义功能的GP，以及问题分解如何导致学习速度显着提高。
We present an adaptation of the standard genetic program (GP) to hierarchically decomposable, multi-agent learning problems. To break down a problem that requires cooperation of multiple agents, we use the team objective function to derive a simpler, intermediate objective function for pairs of cooperating agents. We apply GP to optimize first for the intermediate, then for the team objective function, using the final population from the earlier GP as the initial seed population for the next. This layered learning approach facilitates the discovery of primitive behaviors that can be reused and adapted towards complex objectives based on a shared team goal. We use this method to evolve agents to play a subproblem of robotic soccer (keep-away soccer). Finally, we show how layered learning GP evolves better agents than standard GP, including GP with automatically defined functions, and how the problem decomposition results in a significant learning-speed increase.
DOI：
--
发表时间：
1992
期刊：
--
影响因子：
--
作者：
J. Koza
通讯作者：
J. Koza