Off-Beat Multi-Agent Reinforcement Learning

We investigate cooperative multi-agent reinforcement learning in environments with offbeat actions, i.e., all actions have execution durations. During execution durations, the environmental changes are not synchronised with action executions. To learn efficient multi-agent coordination in environments with offbeat actions, we propose a novel reward redistribution method built on our novel graph-based episodic memory. We name our solution method as LeGEM. Empirical results on stag-hunter game show that it significantly boosts multi-agent coordination.