opendilab/DI-engine

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

Open

#868 opened on Jun 11, 2025

View on GitHubContributor guide
 (0 comments) (0 reactions) (0 assignees)Python (437 forks)github user discovery
envgood first issue

Repository metrics

Stars
 (3,639 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

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.

Contributor guide

Research direction
Investigate the current implementation of hybrid action space in single agent environments (e.g., in DI engine's `hybrid` action type). Study the multi agent framework and understand how actions are handled per agent. Look for any existing examples or issues related to multi agent hybrid actions. Consider proposing a design for extending the support or writing documentation.
Tech stack
python
Domain
machine learningai
Issue type
Research
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
Reinforcement LearningPythonDI engine basics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40