ShangtongZhang/reinforcement-learning-an-introduction resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

14756 stars · 4959 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Python implementations of the figures and examples from Sutton & Barto's 'Reinforcement Learning: An Introduction' (2nd Edition). It serves as a code companion to the textbook, replicating bandit algorithms, dynamic programming, Monte Carlo, and temporal-difference learning results.

Use cases

• study reinforcement learning alongside Sutton & Barto's book
• see working Python code for bandit and gridworld examples
• reproduce textbook figures like epsilon-greedy and UCB curves
• learn dynamic programming and Monte Carlo methods by example
• find reference implementations of TD learning algorithms

When to choose

• you are reading the Sutton & Barto textbook and want matching code
• you want simple, educational implementations rather than a heavy RL framework
• you need to reproduce the book's figures for study or teaching

When to avoid

• you need a production RL training library with GPU support
• you want modern deep RL algorithms like PPO or SAC
• you need exercise solutions for the book

Facets

learning-resource · maturity stable

reinforcement-learning machine-learning data-visualization reinforcement-learning artificial-intelligence machine-learning tutorials python cross-platform sutton-barto educational book-companion python-implementations figures

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ShangtongZhang/reinforcement-learning-an-introduction")