Effective Multi-Agent Deep Reinforcement Learning Control with Relative Entropy Regularization

Chenyang Miao, Yunduan Cui, Huiyun Li, Xinyu Wu
9/26/2023
eess.SYcs.AIcs.LG

Official code: AdrienLin1/MACDPP (13 stars, last commit 2023-09-27).

Abstract

In this paper, a novel Multi-agent Reinforcement Learning (MARL) approach, Multi-Agent Continuous Dynamic Policy Gradient (MACDPP) was proposed to tackle the issues of limited capability and sample efficiency in various scenarios controlled by multiple agents. It alleviates the inconsistency of multiple agents' policy updates by introducing the relative entropy regularization to the Centralized Training with Decentralized Execution (CTDE) framework with the Actor-Critic (AC) structure. Evaluated by multi-agent cooperation and competition tasks and traditional control tasks including OpenAI benchmarks and robot arm manipulation, MACDPP demonstrates significant superiority in learning capability and sample efficiency compared with both related multi-agent and widely implemented signal-agent baselines and therefore expands the potential of MARL in effectively learning challenging control scenarios.

View on arXivView PDF

Code Implementations(1)

AdrienLin1/MACDPPOfficial100%

Code for Paper "Effective Multi-agent Reinforcement Learning Control with Relative Entropy Regularization".

131PythonSep 25, 20233 years ago

Similar Papers

Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

87% match1 repo2.8k2017

K-Level Policy Gradients for Multi-Agent Reinforcement Learning

86% match2025

Structured Cooperative Multi-Agent Reinforcement Learning: a Bayesian Network Perspective

86% match2025

HypeMARL: Multi-Agent Reinforcement Learning For High-Dimensional, Parametric, and Distributed Systems

85% match2025

Preference-Based Multi-Agent Reinforcement Learning: Data Coverage and Algorithmic Techniques

84% match2024

Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization

84% match2023

Cite this paper

@article{miao2023effective,
  title  = {Effective Multi-Agent Deep Reinforcement Learning Control with Relative Entropy Regularization},
  author = {Chenyang Miao and Yunduan Cui and Huiyun Li and Xinyu Wu},
  year   = {2023},
  eprint = {2309.14727},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2309.14727v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.14727.svg)](https://codeofpaper.com/paper/2309.14727)

Discussion