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.

中文翻译：

---

协作多机器人对象操作的分布式强化学习

我们考虑使用强化学习 (RL) 解决协作多机器人对象操作任务。我们提出了两种分布式多智能体 RL 方法：分布式近似 RL (DA-RL)，其中每个智能体应用 Q-learning 和单独的奖励函数；和博弈论 RL (GT-RL)，其中代理根据双矩阵 Q 值游戏的纳什均衡更新其 Q 值。我们在两个模拟机器人手臂的协作对象操作设置中验证了所提出的方法。虽然我们在本文中关注的是一个由两个代理组成的小系统，但 DA-RL 和 GT-RL 都适用于一般的多代理系统，并且有望很好地扩展到大型系统。