https://github.com/j-w-yun/q_learning_tutorial

A TensorFlow implementation of reinforcement learning Q-table and Q-network.
https://github.com/j-w-yun/q_learning_tutorial

Last synced: about 7 hours ago
JSON representation

A TensorFlow implementation of reinforcement learning Q-table and Q-network.

• Host: GitHub
• URL: https://github.com/j-w-yun/q_learning_tutorial
• Owner: j-w-yun
• Created: 2019-05-29T03:41:08.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2019-06-05T05:30:32.000Z (over 5 years ago)
• Last Synced: 2024-03-01T05:07:40.854Z (9 months ago)
• Language: Python
• Size: 14.6 KB
• Stars: 3
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# A TensorFlow implementation of reinforcement learning Q-table and Q-network.

### About

`q_table.py` uses reinforcement learning to generate a Q-table specific to the environment in which it is learned.

`q_network.py` uses reinforcement learning to train a neural network that maps an environment state to an action-value tensor output.

### Dependencies

```

gym 0.12.4

numpy 1.16.3

tensorflow (tensorflow-gpu) 1.13.1

six 1.12.0

```

### Instructions

Clone the repository

`git clone https://github.com/Jaewan-Yun/q_learning_tutorial`

Navigate to folder

`cd q_learning_tutorial`

Run desired tutorial code

`python q_table.py`

`python q_network.py`