MorvanZhou/Reinforcement-learning-with-tensorflow resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

9506 stars · 4983 forks observed · 2026-08-28

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

A collection of simple reinforcement learning tutorial code in Python/TensorFlow, accompanying the Morvan Python (莫烦Python) video course in Chinese and English. It covers algorithms from Q-learning and Sarsa through DQN variants, policy gradients, Actor-Critic, DDPG, A3C, PPO, and curiosity-driven models.

Use cases

• learn reinforcement learning from scratch with code examples
• understand how DQN and its variants work
• implement policy gradient and actor-critic methods
• find PPO and DDPG reference implementations
• follow a video tutorial series on RL algorithms
• practice RL with OpenAI Gym environments

When to choose

• you are a beginner wanting step-by-step RL tutorials with runnable code
• you prefer video-based learning in Chinese or English
• you want minimal, readable implementations of classic RL algorithms

When to avoid

• you need production-ready or well-maintained RL libraries
• you want modern frameworks like RLlib, Stable-Baselines3, or CleanRL
• you need up-to-date TensorFlow 2.x or PyTorch code

Facets

learning-resource · maturity maintenance

reinforcement-learning deep-learning machine-learning reinforcement-learning machine-learning tutorials deep-learning python cross-platform q-learning dqn policy-gradient actor-critic ddpg a3c ppo openai-gym tensorflow tutorials chinese-language

Member repositories

For agents

markdown · JSON · MCP: product_card(name="MorvanZhou/Reinforcement-learning-with-tensorflow")