alpha-zero-general
reversatile
Our great sponsors
alpha-zero-general | reversatile | |
---|---|---|
4 | 1 | |
3,667 | 20 | |
- | - | |
3.1 | 7.7 | |
2 months ago | 4 months ago | |
Jupyter Notebook | C | |
MIT License | GNU General Public License v3.0 only |
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.
alpha-zero-general
-
Competitive reinforcement learning for turn-based games
This is a good intro to alphazero and montecarlo treesearch , Followed by This repo.
- Looking for deeper understanding of AlphaZero algorithm
-
Any interest in a strong Santorini (no powers) AI?
I'm not planning on sharing code at the moment as I'm still working on improving it. The main part of the code is simply from https://github.com/suragnair/alpha-zero-general plus my implementation of game logic (about 100 lines). So for you to use the AI you really need the weights for the neural network. I plan on releasing a better version than the current version in say two months or so.
reversatile
-
What are the best open source games?
No genre specified or Android version specified, so here goes in no particular order: I really enjoy Simon Tatham's Puzzles, Hot Death, Rocks N Diamonds, DroidZebra (its updated successor is Reversatile), Patience Revisited, TuxRider, UnCiv, and HoloKenMod
What are some alternatives?
muzero-general - MuZero
apple-flinger
minigo - An open-source implementation of the AlphaGoZero algorithm
2048-android - The android port of the 2048 game (for offline playing)
tensorflow-onnx - Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX
reversi - Multiplayer Reversi Game on Internet Computer
a3c_trading - Trading with recurrent actor-critic reinforcement learning
hostile-takeover - Open Source Real Time Strategy game based on Warfare Incorporated
Practical_RL - A course in reinforcement learning in the wild
nbsdgames - A package of 18 text-based modern games
Popular-RL-Algorithms - PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..
SelfplayLab - Implementation of the alphago zero algorithm with some small games for experimenting with reinforcement learning