arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.06451cs.AIcs.LG
收藏

通过分叉代理提高强化学习的泛化能力

Improving generalization in reinforcement learning through forked agents

Vrije Universiteit Amsterdam(阿姆斯特丹自由大学);Vrije Universiteit Medical Center Amsterdam(阿姆斯特丹自由大学医学中心)

Olivier Moulin, Vincent Francois-Lavet, Mark Hoogendoorn

摘要:

代理的生态系统,每个都有自己的政策与一些,但有限的,概括性已被证明是一个可靠的方法,以增加跨程序生成的环境的概括性。在这种方法中,当遇到生态系统范围之外的新环境时,新的代理人定期添加到生态系统中。生态系统方法的适应速度和普遍有效性在很大程度上取决于新代理人的启动。在本文中,我们提出了不同的初始化技术,灵感来自深度神经网络初始化和迁移学习,并研究了它们的影响。

英文摘要:

An eco-system of agents each having their own policy with some, but limited, generalizability has proven to be a reliable approach to increase generalization across procedurally generated environments. In such an approach, new agents are regularly added to the eco-system when encountering a new environment that is outside of the scope of the eco-system. The speed of adaptation and general effectiveness of the eco-system approach highly depends on the initialization of new agents. In this paper we propose different initialization techniques, inspired from Deep Neural Network initialization and transfer learning, and study their impact.

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。

↑