# Multi-agent-reinforcement-learning

**Repository Path**: jetingman/Multi-agent-reinforcement-learning

## Basic Information

- **Project Name**: Multi-agent-reinforcement-learning
- **Description**: Implementation of Multi-Agent Reinforcement Learning algorithm(s). Currently includes: MADDPG
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 1
- **Created**: 2023-06-16
- **Last Updated**: 2023-06-16

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Multi-agent Reinforcement Learning

WORK IN PROGRESS

## What's Inside
### - MADDPG
- Implementation of algorithm presented in OpenAI's publication "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments" (Lowe et al., https://arxiv.org/pdf/1706.02275.pdf)
- Does not include "Inferring policies of other agents" and "policy ensembles" 
- multiagent-particle-environment: follow install instructions in https://github.com/openai/multiagent-particle-envs
- Tested on Spread environment.
- TODO:
  - Test on competitive tasks

## Running the code & Dependencies
- Python 3.6
- PyTorch 0.4.1
- multiagent-particle-environment: follow install instructions in https://github.com/openai/multiagent-particle-envs