Networked Agents in the Dark: Team Value Learning under Partial Observability
This addresses the problem of enabling networked agents to cooperate in privacy-sensitive real-world domains with unreliable communication, representing an incremental advance in MARL.
The paper tackles cooperative multi-agent reinforcement learning under partial observability by proposing DNA-MARL, a distributed method using local communication and gradient descent, which achieves superior performance over previous methods in benchmark scenarios.
We propose a novel cooperative multi-agent reinforcement learning (MARL) approach for networked agents. In contrast to previous methods that rely on complete state information or joint observations, our agents must learn how to reach shared objectives under partial observability. During training, they collect individual rewards and approximate a team value function through local communication, resulting in cooperative behavior. To describe our problem, we introduce the networked dynamic partially observable Markov game framework, where agents communicate over a switching topology communication network. Our distributed method, DNA-MARL, uses a consensus mechanism for local communication and gradient descent for local computation. DNA-MARL increases the range of the possible applications of networked agents, being well-suited for real world domains that impose privacy and where the messages may not reach their recipients. We evaluate DNA-MARL across benchmark MARL scenarios. Our results highlight the superior performance of DNA-MARL over previous methods.