GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → geek-ai → Magent

geek-ai / Magent

Licence: mit
A Platform for Many-agent Reinforcement Learning

Programming Languages

python
139335 projects - #7 most used programming language

Labels

deep-learningreinforcement-learning

Projects that are alternatives of or similar to Magent

Run Skeleton Run
Reason8.ai PyTorch solution for NIPS RL 2017 challenge
Stars: ✭ 83 (-93.64%)
Mutual labels:  reinforcement-learning
Magnet
MAGNet: Multi-agents control using Graph Neural Networks
Stars: ✭ 88 (-93.26%)
Mutual labels:  reinforcement-learning
Safeopt
Safe Bayesian Optimization
Stars: ✭ 90 (-93.11%)
Mutual labels:  reinforcement-learning
Reinforcement learning
Reinforcement learning tutorials
Stars: ✭ 82 (-93.72%)
Mutual labels:  reinforcement-learning
Reinforcement Learning For Self Driving Cars
Project on design and implement neural network that maximises driving speed of self-driving car through reinforcement learning.
Stars: ✭ 85 (-93.49%)
Mutual labels:  reinforcement-learning
Mapleai
AI各领域学习资料整理。（A collection of all skills and knowledges should be got command of to obtain an AI relevant job offer. There are online blogs, my personal blogs, electronic books copy.）
Stars: ✭ 89 (-93.19%)
Mutual labels:  reinforcement-learning
Kgpolicy
Reinforced Negative Sampling over Knowledge Graph for Recommendation, WWW2020
Stars: ✭ 83 (-93.64%)
Mutual labels:  reinforcement-learning
Deep Learning Drizzle
Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!
Stars: ✭ 9,717 (+644.03%)
Mutual labels:  reinforcement-learning
Stable Baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Stars: ✭ 1,263 (-3.29%)
Mutual labels:  reinforcement-learning
Tnt
Simple tools for logging and visualizing, loading and training
Stars: ✭ 1,298 (-0.61%)
Mutual labels:  reinforcement-learning
Maze
Maze Applied Reinforcement Learning Framework
Stars: ✭ 85 (-93.49%)
Mutual labels:  reinforcement-learning
Simulator
A ROS/ROS2 Multi-robot Simulator for Autonomous Vehicles
Stars: ✭ 1,260 (-3.52%)
Mutual labels:  reinforcement-learning
Torchrl
Pytorch Implementation of Reinforcement Learning Algorithms ( Soft Actor Critic(SAC)/ DDPG / TD3 /DQN / A2C/ PPO / TRPO)
Stars: ✭ 90 (-93.11%)
Mutual labels:  reinforcement-learning
Sc2aibot
Implementing reinforcement-learning algorithms for pysc2 -environment
Stars: ✭ 83 (-93.64%)
Mutual labels:  reinforcement-learning
Grid2op
Grid2Op a testbed platform to model sequential decision making in power systems.
Stars: ✭ 91 (-93.03%)
Mutual labels:  reinforcement-learning
Tensorflow Tutorials
TensorFlow Tutorials with YouTube Videos
Stars: ✭ 8,919 (+582.92%)
Mutual labels:  reinforcement-learning
Hand dapg
Repository to accompany RSS 2018 paper on dexterous hand manipulation
Stars: ✭ 88 (-93.26%)
Mutual labels:  reinforcement-learning
Cs234
My Solution to Assignments of CS234
Stars: ✭ 91 (-93.03%)
Mutual labels:  reinforcement-learning
Applied Ml
📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.
Stars: ✭ 17,824 (+1264.78%)
Mutual labels:  reinforcement-learning
Categorical Dqn
A working implementation of the Categorical DQN (Distributional RL).
Stars: ✭ 90 (-93.11%)
Mutual labels:  reinforcement-learning
View All Similar Projects ➔

This project is no longer maintained

Please see https://github.com/PettingZoo-Team/MAgent for a maintained fork of this project that's installable with pip.

MAgent

MAgent is a research platform for many-agent reinforcement learning. Unlike previous research platforms that focus on reinforcement learning research with a single agent or only few agents, MAgent aims at supporting reinforcement learning research that scales up from hundreds to millions of agents.

Requirement

MAgent supports Linux and OS X running Python 2.7 or python 3. We make no assumptions about the structure of your agents. You can write rule-based algorithms or use deep learning frameworks.

Install on Linux

git clone [email protected]:geek-ai/MAgent.git
cd MAgent

sudo apt-get install cmake libboost-system-dev libjsoncpp-dev libwebsocketpp-dev

bash build.sh
export PYTHONPATH=$(pwd)/python:$PYTHONPATH

Install on OSX

Note: There is an issue with homebrew for installing websocketpp, please refer to #17

git clone [email protected]:geek-ai/MAgent.git
cd MAgent

brew install cmake llvm [email protected]
brew install jsoncpp argp-standalone
brew tap david-icracked/homebrew-websocketpp
brew install --HEAD david-icracked/websocketpp/websocketpp
brew link --force [email protected]

bash build.sh
export PYTHONPATH=$(pwd)/python:$PYTHONPATH

Docs

Get started

Examples

The training time of following tasks is about 1 day on a GTX1080-Ti card. If out-of-memory errors occur, you can tune infer_batch_size smaller in models.

Note : You should run following examples in the root directory of this repo. Do not cd to examples/.

Train

Three examples shown in the above video. Video files will be saved every 10 rounds. You can use render to watch them.

  • pursuit

     python examples/train_pursuit.py --train

  • gathering

     python examples/train_gather.py --train

  • battle

     python examples/train_battle.py --train

Play

An interactive game to play with battle agents. You will act as a general and dispatch your soldiers.

  • battle game 
    python examples/show_battle_game.py

Baseline Algorithms

The baseline algorithms parameter-sharing DQN, DRQN, a2c are implemented in Tensorflow and MXNet. DQN performs best in our large number sharing and gridworld settings.

Acknowledgement

Many thanks to Tianqi Chen for the helpful suggestions.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].