Metadata-Version: 2.4
Name: jayditya-rl-update
Version: 0.0.1
Summary: Q-learning update helper function (Reinforcement Learning)
Author-email: Jayditya Pratap Singh <example@example.com>
License: MIT
Project-URL: Homepage, https://pypi.org/project/jayditya-rl-update/
Keywords: reinforcement-learning,q-learning,rl
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file


# jayditya-rl-update

A tiny Python package with a single Reinforcement Learning helper function:
`q_learning_update`, which performs a one-step Q-learning update.

## Quick Start

\\`\\`\\`python
from jayditya_rl_update import q_learning_update

q_new = q_learning_update(
    q_value=0.5,
    reward=1.0,
    next_max_q=0.8,
    alpha=0.1,
    gamma=0.99,
)
print(q_new)
\\`\\`\\`

## Installation

\\`\\`\\`
pip install jayditya-rl-update
\\`\\`\\`

