rlcode/reinforcement-learning
Educational repository with clean Python implementations of classic and deep reinforcement learning algorithms for Grid World, CartPole, and Atari environments.
Not currently ranked — collecting fresh signals.
star history
Provides minimal, single-file code examples of reinforcement learning algorithms ranging from basic policy and value iteration to deep methods including DQN, A2C, and PPO. Each algorithm is implemented in a standalone Python file with training on Grid World, CartPole, and Atari environments. Includes benchmark results for training on Apple Silicon using the PyTorch MPS backend.
Frequently asked
- What is rlcode/reinforcement-learning?
- Educational repository with clean Python implementations of classic and deep reinforcement learning algorithms for Grid World, CartPole, and Atari environments.
- Is reinforcement-learning open source?
- Yes — rlcode/reinforcement-learning is open source, released under the MIT license.
- What language is reinforcement-learning written in?
- rlcode/reinforcement-learning is primarily written in Python.
- How popular is reinforcement-learning?
- rlcode/reinforcement-learning has 3.7k stars on GitHub.
- Where can I find reinforcement-learning?
- rlcode/reinforcement-learning is on GitHub at https://github.com/rlcode/reinforcement-learning.