rindow/rindow-rl-gym

A toolkit for developing and comparing reinforcement learning algorithms.

0.1.1 2022-09-24 02:29 UTC

Requires

• php: ^8.0|^8.1
• interop-phpobjects/polite-ai: *
• rindow/rindow-math-matrix: ~1.2.0

Requires (Dev)

• ext-gd: *
• rindow/rindow-math-plot: ~1.0.7

Suggests

• ext-rindow_openblas: 0.3.0 strongly recommended for speed

MIT

• machine learning
• ml
• rindow
• reinforcement
• reinforcement learning
• rl

README

Status:

Gym

Gym is an open source PHP library for developing and comparing reinforcement learning algorithms by providing a standard API to communicate between learning algorithms and environments, as well as a standard set of environments compliant with that API.

Original source codes are the OpenAI Gym.

This is a port of the Python source code to PHP code.