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

2023-09-26Code Available1· sign in to hype

Chenyang Miao, Yunduan Cui, Huiyun Li, Xinyu Wu

Code Available — Be the first to reproduce this paper.

Code

github.com/AdrienLin1/MACDPP
OfficialIn paperpaddle★ 13

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.

Tasks

Deep Reinforcement Learning Multi-agent Reinforcement Learning reinforcement-learning

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

Code

Abstract

Tasks

Reproductions