Metadata-Version: 2.1
Name: rlbandit
Version: 0.1.0
Summary: A simple epsilon-greedy multi-armed bandit RL example
Author: Your Name
License: MIT
Project-URL: Homepage, https://github.com/yourusername/rlbandit
Project-URL: Issues, https://github.com/yourusername/rlbandit/issues
Keywords: reinforcement-learning,epsilon-greedy,multi-armed-bandit
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Requires-Python: >=3.8
Description-Content-Type: text/markdown

# rlbandit

A simple reinforcement learning package implementing an epsilon-greedy multi-armed bandit.

## Usage
```python
from rlbandit import run_bandit

result = run_bandit(n_arms=5, epsilon=0.1, trials=1000, seed=42)
print("True probabilities:", result["true_probs"])
print("Total reward:", result["total_reward"])
print("Average reward:", result["average_reward"])
print("Arm counts:", result["counts"])
