rl-simple-teerth 0.1.0

Simple RL utilities for epsilon-greedy and TD error

# RL Simple Package by Teerth

A simple Python package for Reinforcement Learning utilities created by **Teerth** for academic assignment.

## Installation

pip install rl_simple_teerth

## Features

- **Epsilon-Greedy Action Selection**: Balance exploration and exploitation

- **TD Error Calculation**: Compute temporal difference errors

## Usage

from rl_simple import epsilon_greedy_action, calculate_td_error

Epsilon-greedy selection

Q_values = [0.1, 0.8, 0.3]

action = epsilon_greedy_action(Q_values, epsilon=0.1)

print(f"Selected action: {action}")

TD error

td_error = calculate_td_error(reward=1.0, gamma=0.9,

current_value=0.5, next_value=0.8)

print(f"TD Error: {td_error}")

## Author

**Teerth**

Created for Reinforcement Learning Assignment