Trustable Policy Collaboration Scheme for Multi-Agent Stigmergic Reinforcement Learning

In this letter, we propose a trustable policy collaboration scheme in the paradigm of multi-agent independent reinforcement learning (MAIRL). This trustable policy collaboration scheme is realized by directly mixing the policy parameters of homogeneous agents, for which an upper bound of the mixture metric is derived to guarantee the policy improvement. This trustable policy collaboration scheme can update the behavioral policies of agents distributedly and further improve the performance of MAIRL. In addition, we develop a practical implementation of this trustable policy collaboration scheme, and verify its effectiveness in a mixed-autonomy traffic control simulation scenario through the performance comparison with other typical methods.