Distributed primal-dual algorithm for constrained multi-agent reinforcement learning under coupled policies
By: Pengcheng Dai , He Wang , Dongming Wang and more
Potential Business Impact:
Helps robots work together safely without sharing secrets.
In this work, we investigate constrained multi-agent reinforcement learning (CMARL), where agents collaboratively maximize the sum of their local objectives while satisfying individual safety constraints. We propose a framework where agents adopt coupled policies that depend on both local states and parameters, as well as those of their $κ_p$-hop neighbors, with $κ_p>0$ denoting the coupling distance. A distributed primal-dual algorithm is further developed under this framework, wherein each agent has access only to state-action pairs within its $2κ_p$-hop neighborhood and to reward information within its $κ+ 2κ_p$-hop neighborhood, with $κ> 0$ representing the truncation distance. Moreover, agents are not permitted to directly share their true policy parameters or Lagrange multipliers. Instead, each agent constructs and maintains local estimates of these variables for other agents and employs such estimates to execute its policy. Additionally, these estimates are further updated and exchanged exclusively through an independent, time-varying networks, which enhances the overall system security. We establish that, with high probability, our algorithm can achieve an $ε$-first-order stationary convergence with an approximation error of $\mathcal{O}(γ^{\frac{κ+1}{κ_{p}}})$ for discount factor $γ\in(0,1)$. Finally, simulations in GridWorld environment are conducted to demonstrate the effectiveness of the proposed algorithm.
Similar Papers
Structured Cooperative Multi-Agent Reinforcement Learning: a Bayesian Network Perspective
Multiagent Systems
Helps many robots learn to work together better.
HypeMARL: Multi-Agent Reinforcement Learning For High-Dimensional, Parametric, and Distributed Systems
Machine Learning (CS)
Helps many robots work together to control complex systems.
Policy Optimization in Multi-Agent Settings under Partially Observable Environments
Multiagent Systems
Helps robots learn together faster.