Learning Heterogeneous Agent Cooperation via Multiagent League Training
This work addresses the problem of training diverse agents in multiagent systems for researchers and practitioners, representing an incremental advancement with a novel method for a known bottleneck.
The paper tackles the challenges of heterogeneous multiagent reinforcement learning, such as non-stationarity and policy version iteration, by proposing Heterogeneous League Training (HLT), which improves success rates in cooperative tasks and addresses these issues effectively.
Many multiagent systems in the real world include multiple types of agents with different abilities and functionality. Such heterogeneous multiagent systems have significant practical advantages. However, they also come with challenges compared with homogeneous systems for multiagent reinforcement learning, such as the non-stationary problem and the policy version iteration issue. This work proposes a general-purpose reinforcement learning algorithm named Heterogeneous League Training (HLT) to address heterogeneous multiagent problems. HLT keeps track of a pool of policies that agents have explored during training, gathering a league of heterogeneous policies to facilitate future policy optimization. Moreover, a hyper-network is introduced to increase the diversity of agent behaviors when collaborating with teammates having different levels of cooperation skills. We use heterogeneous benchmark tasks to demonstrate that (1) HLT promotes the success rate in cooperative heterogeneous tasks; (2) HLT is an effective approach to solving the policy version iteration problem; (3) HLT provides a practical way to assess the difficulty of learning each role in a heterogeneous team.