Skip to main content

table-rl, an online tabular reinforcement learning library

Project description

table-rl

This repository contains a set of implementations and functionality of purely online tabular reinforcement learning algorithms.

Currently we support Python 3.8.

Installation

You should be able to install table-rl from PyPi.

pip3 install table-rl

You can also install table-rl from source.

git clone https://github.com/prabhatnagarajan/table-rl.git
cd table-rl
pip3 install -e .

How the library works

Reward functions, value functions, transition functions are all numpy arrays and matrices. We follow the conventions from Sutton and Barto's RL Book.

We focus only on online algorithms that interact with and get experience from the environment in a purely online way.

Contributing

Use pytest on the test directories.

python -m pytest tests/

License

MIT License.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

table_rl-0.1.0.tar.gz (11.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

table_rl-0.1.0-py3-none-any.whl (14.5 kB view details)

Uploaded Python 3

File details

Details for the file table_rl-0.1.0.tar.gz.

File metadata

  • Download URL: table_rl-0.1.0.tar.gz
  • Upload date:
  • Size: 11.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.9.17

File hashes

Hashes for table_rl-0.1.0.tar.gz
Algorithm Hash digest
SHA256 280393dece30b174d602df40a35143cbaaf3d24442bcdf11fb29bd54a211dab8
MD5 c8f0ed577bec363344bf87a044af831f
BLAKE2b-256 1804715863c245adde236a9cb6d6559b6aeee913aaf8789a9b22113693c1dbcf

See more details on using hashes here.

File details

Details for the file table_rl-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: table_rl-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 14.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.9.17

File hashes

Hashes for table_rl-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 9d79a4ce0ae1e915e654657758cfcfce1861fcbf445d7f13f35e266a91144d0a
MD5 e308cbf31671e3fbc189d538aaf2cf6f
BLAKE2b-256 59d210a7fabd56aec9dc870e3f295ad67a8eae787a4410b2a7635a02a93fc3c4

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page