https://github.com/takuseno/rsvg

Recurrent Stochastic Value Gradient implementation with TensorFlow
https://github.com/takuseno/rsvg

reinforcement-learning tensorflow

Last synced: about 1 month ago
JSON representation

Recurrent Stochastic Value Gradient implementation with TensorFlow

• Host: GitHub
• URL: https://github.com/takuseno/rsvg
• Owner: takuseno
• Created: 2017-12-07T05:06:19.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2018-04-22T08:20:48.000Z (over 6 years ago)
• Last Synced: 2024-10-23T04:06:21.293Z (2 months ago)
• Topics: reinforcement-learning, tensorflow
• Language: Python
• Size: 11.7 KB
• Stars: 7
• Watchers: 3
• Forks: 3
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
## RSVG

Recurrent Stochastic Value Gradient implementation with Tensorflow.

https://arxiv.org/pdf/1512.04455.pdf

## requirements

- Python3

## dependencies

- tensorflow

- gym[atari]

- opencv-python

- git+https://github.com/imai-laboratory/lightsaber

## usage

### training

```

$ python train.py [--render] --final-steps 10000000

```

### playing

```

$ python train.py [--render] --load {path of models} --demo

```

### implementation

This is inspired by following projects.

- [DQN](https://github.com/imai-laboratory/dqn)