论文标题
合作多机器人对象操纵的分布式加固学习
Distributed Reinforcement Learning for Cooperative Multi-Robot Object Manipulation
论文作者
论文摘要
我们考虑使用增强学习（RL）解决合作的多机器人对象操纵任务。我们提出了两种分布式多代理RL方法：分布式近似RL（DA-RL），每个代理都使用Q学习，并使用个体奖励功能；和游戏理论RL（GT-RL），代理商根据Bimatrix Q-Value游戏的NASH平衡来更新其Q值。我们在使用两个模拟机器人臂进行合作对象操纵的情况下验证了所提出的方法。尽管我们专注于本文的两种代理的小型系统，但DA-RL和GT-RL都适用于一般的多代理系统，并有望很好地扩展到大型系统。
We consider solving a cooperative multi-robot object manipulation task using reinforcement learning (RL). We propose two distributed multi-agent RL approaches: distributed approximate RL (DA-RL), where each agent applies Q-learning with individual reward functions; and game-theoretic RL (GT-RL), where the agents update their Q-values based on the Nash equilibrium of a bimatrix Q-value game. We validate the proposed approaches in the setting of cooperative object manipulation with two simulated robot arms. Although we focus on a small system of two agents in this paper, both DA-RL and GT-RL apply to general multi-agent systems, and are expected to scale well to large systems.
