Code

Getting Started

Clone the repository and set up the environment:

git clone https://example.com/rl-explained-code.git
cd rl-explained-code
python -m venv .venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate
pip install -r requirements.txt
      

Minimal Bandit Example

# epsilon_greedy.py
import random
import statistics

def run(eps=0.1, steps=1000, arms=[0.1, 0.3, 0.6]):
    Q = [0.0]*len(arms); N = [0]*len(arms)
    rewards=[]
    for t in range(steps):
        a = random.randrange(len(arms)) if random.random()