超级会员免费看
本文提出了一种结合进化过程与强化学习的方法，称为POEM（Policy Optimization While Evolving Morphology），用于发现优秀身体结构与策略的智能体。研究中，作者通过将RL与进化算法结合，在类似Robo-Sumo的环境中，展示了该方法能够生成性能显著优于仅优化策略的基线智能体。此外，还提出了一种利用合作博弈论中的夏普利值来评估个体身体组件对性能贡献的方法，考虑了组件间的协同效应。
ABSTRACT
Reinforcement learning (RL) has proven to be a powerful paradigm for deriving complex behaviors from simple reward signals in a wide range of environments. When applying RL to continuous control agents in simulated physics environ-ments, the body is usually considered to be part of the environment. However, during evolution the physical body of biological organisms and their controlling brains are co-evolved, thus exploring a much larger space of actuator/controller configurations. Put differently, the intelligence does not reside only in the agent’s mind, but also in the design of their body. We propose a method for uncovering strong agents, consisting of a good combination of a body and policy, based on combining RL with an evolutionary proced
订阅专栏 解锁全文
扫一扫
3504
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
