https://github.com/deepmind/hanabi-learning-environment
hanabi_learning_environment is a research platform for Hanabi experiments.
https://github.com/deepmind/hanabi-learning-environment
Last synced: 3 months ago
JSON representation
hanabi_learning_environment is a research platform for Hanabi experiments.
- Host: GitHub
- URL: https://github.com/deepmind/hanabi-learning-environment
- Owner: google-deepmind
- License: apache-2.0
- Archived: true
- Created: 2019-01-31T08:42:56.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2023-02-14T19:19:46.000Z (over 2 years ago)
- Last Synced: 2025-08-11T10:26:46.342Z (3 months ago)
- Language: Python
- Homepage:
- Size: 137 KB
- Stars: 654
- Watchers: 29
- Forks: 157
- Open Issues: 22
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
- awesome-ai-agent-testing - Hanabi - Cooperative multi-agent card game. (Benchmarks and Evaluation / Datasets)
README
This is not an officially supported Google product.
hanabi\_learning\_environment is a research platform for Hanabi experiments. The file rl\_env.py provides an RL environment using an API similar to OpenAI Gym. A lower level game interface is provided in pyhanabi.py for non-RL methods like Monte Carlo tree search.
### Getting started
Install the learning environment:
```
sudo apt-get install g++ # if you don't already have a CXX compiler
sudo apt-get install python-pip # if you don't already have pip
pip install . # or pip install git+repo_url to install directly from github
```
Run the examples:
```
pip install numpy # game_example.py uses numpy
python examples/rl_env_example.py # Runs RL episodes
python examples/game_example.py # Plays a game using the lower level interface
```