All Projects → tobegit3hub → deep_q

tobegit3hub / deep_q

Licence: Apache-2.0 license
Deep reinforcement learning with TensorFlow

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Deep Q

Introduction

The deep reinforcement learning example with TensorFlow.

It's based on gym and Q-learning algorithm. It provides the trainable example with native TensorFlow APIs and you can use it for all gym games.

Usage

CartPole

./play_game.py

MountainCar

./play_game.py --mode train --gym_env MountainCar-v0 --checkpoint ./checkpoint_mountain

Pacman

./play_game.py --mode train --gym_env MsPacman-v0 --checkpoint ./checkpoint_pacman --model cnn

Test

./play_game.py --mode untrained
./play_game.py --mode inference
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].