# hmp

**Repository Path**: hh505030475/hmp

## Basic Information

- **Project Name**: hmp
- **Description**: Hybrid Multiagent Playground, a reinforcement learning framework for swarm intelligence.
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 1
- **Created**: 2021-04-27
- **Last Updated**: 2022-05-31

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

Author: Qingxu Fu, CASIA

# What is HMP
Hybrid Multiagent Playground (HMP) is a multiagent ML framework for research.
Designed to support multiagent simulation environments 
by thorough Mission-Algorithm separation and modularization.
Currently, the primary objective of HMP is to support RL research,
especially multiagent RL.
the 

# usage

## <1> all default
launch with: 
python main.py

## <2> change settings
launch with: 
python main.py --cfg xx.json




# project road map
If you are interested in something, you may continue to read:

    Handling parallel environment             -->   task_runner.py & shm_env.py

    Link between teams and diverse algorithms -->   multi_team.py

    Adding new env                            -->   MISSIONS.env_router.py

    Adding algorithm                          -->   ALGORITHM.example_foundation.py

    Configuring by writing py files           -->   config.py

    Configuring by json                       -->   xx.json

    colorful printing                         -->   colorful.py

    auto pip deployer                         -->   pip_find_missing.py

    efficient parallel execting               -->   shm_pool.pyx

    auto gpu selection                        -->   auto_gpu.py

    matlab logging/plotting bridge            -->   mcom.py & mcom_rec.py

    experiment batch executor                 -->   mprofile.py