aloooha / dqn

Play CartPole through DQN

Tensorflow implementation of [Human-Level Control through Deep Reinforcement Learning]

This implementation contains:

1. Deep Q-network
2. Experience replay memory
   • to reduce the correlations between consecutive updates
3. Network for Q-learning targets are fixed for intervals
   • to reduce the correlations between target and predicted Q-values

Algorithm:

target network update model:

Requirements

• Python 3
• gym
• TensorFlow 1.8.0
• Tensorlayer 1.8.5

Usage

First, install prerequisites with:

$ pip install gym
$ pip install tensorlayer

To train a model:

$ python main.py

if you want to see the display, modify the code main.py

display = True

To see the train log in tensorboard:

$ tensorboard --logdir=./result/tensorboard

References

• Playing Atari with Deep Reinforcement Learning
• Human-level control through deep reinforcement learning

License

GPLv3