opendilab/DI-engine

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

Aperta

#868 aperta il 11 giu 2025

 (0 commenti) (0 reazioni) (0 assegnatari)Python (437 fork)github user discovery
envgood first issue

Metriche repository

Star
 (3639 stelle)
Metriche merge PR
 (Nessuna PR mergiata in 30 g)

Descrizione

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.

Guida contributor