andri27-ts/Reinforcement-Learning resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

4737 stars · 669 forks observed · 2026-08-28

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

A 60-day structured course for learning Deep Reinforcement Learning, combining curated lectures (mainly from DeepMind and Berkeley) with PyTorch implementations of core algorithms like DQN, A2C, and PPO. Code is tested on OpenAI Gym environments including Atari and RoboSchool.

Use cases

• learn deep reinforcement learning from scratch
• find a structured RL study plan
• see PyTorch implementations of DQN and PPO
• understand actor-critic and policy gradient algorithms
• practice RL algorithms on OpenAI Gym environments
• follow a 60-day reinforcement learning challenge

When to choose

• you want a guided, time-boxed curriculum for deep RL
• you prefer learning by reading lectures and reading clean PyTorch code
• you already know basic Python, PyTorch, and deep learning fundamentals

When to avoid

• you need a production-ready RL library or framework
• you want actively maintained code with recent updates (last release 2020)
• you are a complete beginner without ML or deep learning background

Facets

learning-resource · maturity maintenance

reinforcement-learning deep-learning machine-learning reinforcement-learning deep-learning machine-learning tutorials artificial-intelligence python cross-platform pytorch openai-gym dqn ppo a2c q-learning policy-gradients 60-days-challenge jupyter-notebooks course

Member repositories

For agents

markdown · JSON · MCP: product_card(name="andri27-ts/Reinforcement-Learning")