Distributed Reinforcement Learning for Cooperative Multi-Robot Object Manipulation
This addresses coordination challenges in multi-robot systems, but it is incremental as it builds on existing RL methods.
The paper tackled cooperative multi-robot object manipulation by proposing two distributed multi-agent reinforcement learning approaches, DA-RL and GT-RL, and validated them with two simulated robot arms, showing applicability to general systems.
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.