BriefGPT.xyz
Jul, 2018
多智能体生成对抗模仿学习
Multi-Agent Generative Adversarial Imitation Learning
HTML
PDF
Jiaming Song, Hongyu Ren, Dorsa Sadigh, Stefano Ermon
TL;DR
本文提出了一种新的适用于多智能体环境的 Multi-Agent 模仿学习框架,它建立在广义反向强化学习的基础上,并引入了实用的多智能体演员-评论家算法。该方法可用于多个合作或竞争代理的高维环境中模仿复杂的行为。
Abstract
imitation learning
algorithms can be used to learn a policy from expert demonstrations without access to a reward signal. However, most existing approaches are not applicable in
multi-agent settings
due to the ex
→