Learning Multi-agent Skills for Tabular Reinforcement Learning using Factor Graphs
This addresses the challenge of exponential state space growth in multi-agent systems, enabling more efficient exploration for collaborative tasks.
The paper tackles the problem of extending skill discovery to multi-agent reinforcement learning by approximating the joint state space as a Kronecker graph and using Laplacian spectra to compute multi-agent options, resulting in significantly faster exploration and higher cumulative rewards in collaborative tasks.
Covering skill (a.k.a., option) discovery has been developed to improve the exploration of reinforcement learning in single-agent scenarios with sparse reward signals, through connecting the most distant states in the embedding space provided by the Fiedler vector of the state transition graph. However, these option discovery methods cannot be directly extended to multi-agent scenarios, since the joint state space grows exponentially with the number of agents in the system. Thus, existing researches on adopting options in multi-agent scenarios still rely on single-agent option discovery and fail to directly discover the joint options that can improve the connectivity of the joint state space of agents. In this paper, we show that it is indeed possible to directly compute multi-agent options with collaborative exploratory behaviors among the agents, while still enjoying the ease of decomposition. Our key idea is to approximate the joint state space as a Kronecker graph -- the Kronecker product of individual agents' state transition graphs, based on which we can directly estimate the Fiedler vector of the joint state space using the Laplacian spectrum of individual agents' transition graphs. This decomposition enables us to efficiently construct multi-agent joint options by encouraging agents to connect the sub-goal joint states which are corresponding to the minimum or maximum values of the estimated joint Fiedler vector. The evaluation based on multi-agent collaborative tasks shows that the proposed algorithm can successfully identify multi-agent options, and significantly outperforms prior works using single-agent options or no options, in terms of both faster exploration and higher cumulative rewards.