Deep-Reinforcement-Learning-With-Python
Master classic RL, deep RL, distributional RL, inverse RL, and more using OpenAI Gym and TensorFlow with extensive Math
- 480
- Jupyter Notebook
- 6 y ago
Master classic RL, deep RL, distributional RL, inverse RL, and more using OpenAI Gym and TensorFlow with extensive Math
Learn Tabular Q-Learning, $\varepsilon$-greedy exploration, and Bellman Dynamic Programming in the browser with interactive Tic-Tac-Toe. Zero dependencies.
This project aims to explore the basic concepts of Reinforcement Learning using the FrozenLake environment from the OpenAI Gym library.