Continuous-Time Distributed Dynamic Programming for Networked Multi-Agent Markov Decision Processes
This work addresses coordination challenges in multi-agent systems, such as robotics or sensor networks, by enabling distributed learning without global reward knowledge, though it appears incremental as it builds on existing distributed optimization methods.
The paper tackles the problem of continuous-time distributed dynamic programming for networked multi-agent Markov decision processes, where agents only know their own rewards and share parameters via a communication network, and it introduces two novel distributed DP algorithms with proven convergence.
The main goal of this paper is to investigate continuous-time distributed dynamic programming (DP) algorithms for networked multi-agent Markov decision problems (MAMDPs). In our study, we adopt a distributed multi-agent framework where individual agents have access only to their own rewards, lacking insights into the rewards of other agents. Moreover, each agent has the ability to share its parameters with neighboring agents through a communication network, represented by a graph. We first introduce a novel distributed DP, inspired by the distributed optimization method of Wang and Elia. Next, a new distributed DP is introduced through a decoupling process. The convergence of the DP algorithms is proved through systems and control perspectives. The study in this paper sets the stage for new distributed temporal different learning algorithms.