Group-Agent Reinforcement Learning with Heterogeneous Agents
This addresses the challenge of efficient multi-agent learning in heterogeneous settings, which is incremental but offers practical gains for reinforcement learning applications.
The paper tackles the problem of improving individual agent learning performance in group-agent reinforcement learning with heterogeneous agents, achieving a 96% learning speed-up rate and 72% of agents learning over 100 times faster in experiments on 43 Atari games.
Group-agent reinforcement learning (GARL) is a newly arising learning scenario, where multiple reinforcement learning agents study together in a group, sharing knowledge in an asynchronous fashion. The goal is to improve the learning performance of each individual agent. Under a more general heterogeneous setting where different agents learn using different algorithms, we advance GARL by designing novel and effective group-learning mechanisms. They guide the agents on whether and how to learn from action choices from the others, and allow the agents to adopt available policy and value function models sent by another agent if they perform better. We have conducted extensive experiments on a total of 43 different Atari 2600 games to demonstrate the superior performance of the proposed method. After the group learning, among the 129 agents examined, 96% are able to achieve a learning speed-up, and 72% are able to learn over 100 times faster. Also, around 41% of those agents have achieved a higher accumulated reward score by learning in less than 5% of the time steps required by a single agent when learning on its own.