MorvanZhou/Reinforcement-learning-with-tensorflow
Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学
Implements foundational to state-of-the-art RL algorithms (Q-learning, DQN variants, policy gradients, A3C, PPO) with TensorFlow, progressing from tabular methods to deep neural network approaches. Each algorithm includes standalone implementations with OpenAI Gym integration and visual demonstrations on control tasks like robot locomotion and lunar landing. The curriculum structure bridges classic RL theory with modern deep RL techniques through progressive complexity.
9,435 stars. No commits in the last 6 months.
Stars
9,435
Forks
5,011
Language
Python
License
MIT
Category
Last pushed
Mar 31, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MorvanZhou/Reinforcement-learning-with-tensorflow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
google-deepmind/dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning...
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Denys88/rl_games
RL implementations
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
flatland-association/flatland-rl
The Flatland Framework is a multi-purpose environment to tackle problems around resilient...