opendilab/DI-engine

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

開放

#868 建立於 2025年6月11日

 (0 則留言) (0 個反應) (0 位負責人)Python (436 個分叉)github user discovery
envgood first issue

倉庫指標

星標
 (3,638 顆星)
PR 合併指標
 (30 天內沒有已合併 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.

貢獻者指南