https://github.com/dustinvtran/bayesrl

A Python library for reinforcement learning using Bayesian approaches
https://github.com/dustinvtran/bayesrl

Last synced: 22 days ago
JSON representation

A Python library for reinforcement learning using Bayesian approaches

• Host: GitHub
• URL: https://github.com/dustinvtran/bayesrl
• Owner: dustinvtran
• License: mit
• Created: 2015-04-13T23:33:40.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2015-05-14T21:47:42.000Z (over 9 years ago)
• Last Synced: 2024-10-10T12:50:51.839Z (about 1 month ago)
• Language: Python
• Homepage:
• Size: 18.5 MB
• Stars: 51
• Watchers: 8
• Forks: 12
• Open Issues: 6
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# BayesRL

`BayesRL` is a Python library for reinforcement learning using Bayesian

approaches. It stores both agents and environments under separate classes, where

an agent class is a learning algorithm and environments are tasks that the agent

must solve. We include agents and environments for solving and implementing both

Markov decision processes (MDPs) and partially observable Markov decision

processes (POMDPs).

Examples can be found in the directory `tests/`. More documentation can be found in the [wiki](../../wiki).

## Installation

To install from pip, run

```{bash}

pip install -e "git+https://github.com/dustinvtran/bayesrl.git#egg=bayesrl"

```

## Authors

* Dustin Tran \

* Xiaomin Wang \

* Rodrigo Gomes \

## References

* Malcolm Strens. A bayesian framework for reinforcement learning. In _Proceedings of the 17th International Conference on Machine Learning (ICML)_, 2000.