多智能体深度强化学习的协作探索

Jul, 2021

Cooperative Exploration for Multi-Agent Deep Reinforcement Learning

Iou-Jen Liu, Unnat Jain, Raymond A. Yeh, Alexander G. Schwing

TL;DR本文提出协作多智能体探索（CMAE）方法，通过归一化熵技术从多个状态空间中选择目标，实现智能体之间探索的协调性，取得了多项任务的良好表现。

Abstract

exploration is critical for good results in deep reinforcement learning and has attracted much attention. However, existing multi-agent deep rein