opendilab/DI-engine

How to increase the hybrid action space in multi-agent environments

开放

#868 创建于 2025年6月11日

 (0 条评论) (0 个反应) (0 位负责人)Python (437 个派生)github user discovery
envgood first issue

仓库指标

星标
 (3,639 个星标)
PR 合并指标
 (30 天内没有已合并 PR)

描述

I need to develop a multi-agent cooperative environment where each agent has a mixed action space consisting of discrete and continuous actions. How should I select and modify the corresponding algorithms in DI? Currently, it seems that the mixed action space in DI only supports single-agent situations.

贡献者指南