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 → starry-sky6688 → Starcraft

starry-sky6688 / Starcraft

Implementations of IQL, QMIX, VDN, COMA, QTRAN, MAVEN, CommNet, DyMA-CL, and G2ANet on SMAC, the decentralised micromanagement scenario of StarCraft II

Programming Languages

python
139335 projects - #7 most used programming language

Labels

reinforcement-learningdeep-reinforcement-learning

Projects that are alternatives of or similar to Starcraft

Lagom
lagom: A PyTorch infrastructure for rapid prototyping of reinforcement learning algorithms.
Stars: ✭ 364 (-2.15%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Pytorch Trpo
PyTorch implementation of Trust Region Policy Optimization
Stars: ✭ 303 (-18.55%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Tensorforce
Tensorforce: a TensorFlow library for applied reinforcement learning
Stars: ✭ 3,062 (+723.12%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Tf2rl
TensorFlow2 Reinforcement Learning
Stars: ✭ 353 (-5.11%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Openai lab
An experimentation framework for Reinforcement Learning using OpenAI Gym, Tensorflow, and Keras.
Stars: ✭ 313 (-15.86%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Rlgraph
RLgraph: Modular computation graphs for deep reinforcement learning
Stars: ✭ 272 (-26.88%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Pytorch Soft Actor Critic
PyTorch implementation of soft actor critic
Stars: ✭ 300 (-19.35%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Reinforcement Learning
Minimal and Clean Reinforcement Learning Examples
Stars: ✭ 2,863 (+669.62%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Reward Learning Rl
[RSS 2019] End-to-End Robotic Reinforcement Learning without Reward Engineering
Stars: ✭ 310 (-16.67%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Neural Symbolic Machines
Neural Symbolic Machines is a framework to integrate neural networks and symbolic representations using reinforcement learning, with applications in program synthesis and semantic parsing.
Stars: ✭ 305 (-18.01%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Drq
DrQ: Data regularized Q
Stars: ✭ 268 (-27.96%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Deeprl Tensorflow2
🐋 Simple implementations of various popular Deep Reinforcement Learning algorithms using TensorFlow2
Stars: ✭ 319 (-14.25%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Rad
RAD: Reinforcement Learning with Augmented Data
Stars: ✭ 268 (-27.96%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Curl
CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning
Stars: ✭ 346 (-6.99%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Gym Gazebo2
gym-gazebo2 is a toolkit for developing and comparing reinforcement learning algorithms using ROS 2 and Gazebo
Stars: ✭ 257 (-30.91%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Deep rl
PyTorch implementations of Deep Reinforcement Learning algorithms (DQN, DDQN, A2C, VPG, TRPO, PPO, DDPG, TD3, SAC, SAC-AEA)
Stars: ✭ 291 (-21.77%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Roboleague
A car soccer environment inspired by Rocket League for deep reinforcement learning experiments in an adversarial self-play setting.
Stars: ✭ 236 (-36.56%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Learningx
Deep & Classical Reinforcement Learning + Machine Learning Examples in Python
Stars: ✭ 241 (-35.22%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Gdrl
Grokking Deep Reinforcement Learning
Stars: ✭ 304 (-18.28%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
Reinforcement Learning
Learn Deep Reinforcement Learning in 60 days! Lectures & Code in Python. Reinforcement Learning + Deep Learning
Stars: ✭ 3,329 (+794.89%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning
View All Similar Projects ➔

StarCraft

Pytorch implementations of the multi-agent reinforcement learning algorithms, including IQL, QMIX, VDN, COMA, QTRAN(both QTRAN-base and QTRAN-alt), MAVEN, CommNet, DyMA-CL, and G2ANet, which are the state of the art MARL algorithms. In addition, because CommNet and G2ANet need an external training algorithm, we provide Central-V and REINFORCE for them to training, you can also combine them with COMA. We trained these algorithms on SMAC, the decentralised micromanagement scenario of StarCraft II.

Corresponding Papers

Requirements

Acknowledgement

TODO List

  • [x] Add CUDA option
  • [x] DyMA-CL
  • [x] G2ANet
  • [x] MAVEN
  • [ ] VBC
  • [ ] Other SOTA MARL algorithms
  • [ ] Update results on other maps

Quick Start

$ python main.py --map=3m --alg=qmix

Directly run the main.py, then the algorithm will start training on map 3m. Note CommNet and G2ANet need an external training algorithm, so the name of them are like reinforce+commnet or central_v+g2anet, all the algorithms we provide are written in ./common/arguments.py.

If you just want to use this project for demonstration, you should set --evaluate=True --load_model=True.

The running of DyMA-CL is independent from others because it requires different environment settings, so we put it on another project. For more details, please read DyMA-CL documentation.

Result

We independently train these algorithms for 8 times and take the mean of the 8 independent results, and we evaluate them for 20 episodes every 100 training steps. All of the results are saved in ./result. Results on other maps are still in training, we will update them later.

1. Mean Win Rate of 8 Independent Runs on 3m --difficulty=7(VeryHard)

2. Mean Win Rate of 8 Independent Runs on 8m --difficulty=7(VeryHard)

3. Mean Win Rate of 8 Independent Runs on 2s3z --difficulty=7(VeryHard)

Replay

If you want to see the replay, make sure the replay_dir is an absolute path, which can be set in ./common/arguments.py. Then the replays of each evaluation will be saved, you can find them in your path.

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].