pysc2
stable-baselines
pysc2 | stable-baselines | |
---|---|---|
6 | 10 | |
7,915 | 4,000 | |
0.2% | - | |
3.1 | 0.0 | |
10 months ago | over 1 year ago | |
Python | Python | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
pysc2
- Project For Beginners [StarCraft 2 AI]
-
[D] What tool do you use for reinforcement learning experimentation?
Good evening, guys. I currently use StarCraft 2 as a tool for experimenting with my deep reinforcement learning projects, I have also used OpenAI Gym.
-
[D] Which GPU cloud do you use and recommend?
DRL experiments using StarCraft II Learning Environment.
- How A.I. Conquered Poker
-
Tips for a beginner
If you are looking to develop a machine-learning based bot you can go with pysc2: https://github.com/deepmind/pysc2
-
How AI works in big RTS games?
in terms of deepmind: https://github.com/deepmind/pysc2 source code if you want to take a look.
stable-baselines
-
Distributed implementation tips
As underlined by gold-panda, you can give a try with multiprocessing. I once implemented a version based on what is done in stable_baselines v1 (https://github.com/hill-a/stable-baselines/blob/master/stable_baselines/common/vec_env/subproc_vec_env.py)
-
GAIL without actions?
Found relevant code at https://github.com/hill-a/stable-baselines + all code implementations here
-
Best framework to use if learning today
Depends what you wanna do. Universal answer would be https://stable-baselines.readthedocs.io/
-
weird mean reward graph
As you will see here it is recommended to augment this safety measure with target kl_divergence, that will ensure even smoother learning and enforce early stopping to prevent learning collapses.
-
Nvidia ISAAC gym/RL
Code for https://arxiv.org/abs/1707.06347 found: https://github.com/hill-a/stable-baselines
- Bounds for observation
-
Understanding multi agent learning in OpenAI gym and stable-baselines
I haven't read the code, but stable-baselines doesn't support multi-agent environments (https://github.com/hill-a/stable-baselines/issues/423), so I think they're trying to make learning multi-agent easier with Environment.train().
- Using Reinforment Learning to beat the first boss in Dark souls 3 with Proximal Policy Optimization
-
Reinforcement Learning Crash Course (Free)
- https://github.com/hill-a/stable-baselines (Tensorflow)
-
JAX Implementations of Actor-Critic Algorithms
- tf2 speed: https://github.com/hill-a/stable-baselines/issues/576#issuecomment-573331715
What are some alternatives?
python-sc2 - A StarCraft II bot api client library for Python 3
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
lolgym - PyLoL OpenAI Gym Environments for League of Legends v4.20 RL Environment (LoLRLE)
Ray - Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
smac - SMAC: The StarCraft Multi-Agent Challenge
rl-baselines3-zoo - A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
Galaxy-Observer-UI - Toolset to create Observer Interfaces for StarCraft II / Heroes of the Storm. https://ahli.github.io/Galaxy-Observer-UI/#/
Super-mario-bros-PPO-pytorch - Proximal Policy Optimization (PPO) algorithm for Super Mario Bros
gym - A toolkit for developing and comparing reinforcement learning algorithms.
Tic-Tac-Toe-Gym - This is the Tic-Tac-Toe game made with Python using the PyGame library and the Gym library to implement the AI with Reinforcement Learning
s2client-proto - StarCraft II Client - protocol definitions used to communicate with StarCraft II.
DI-engine - OpenDILab Decision AI Engine