https://github.com/neka-nat/async-rl-noreward

Keras implementation of Curiosity-driven Exploration by Self-supervised Prediction
https://github.com/neka-nat/async-rl-noreward

a3c deep-reinforcement-learning keras super-mario

Last synced: 4 days ago
JSON representation

Keras implementation of Curiosity-driven Exploration by Self-supervised Prediction

• Host: GitHub
• URL: https://github.com/neka-nat/async-rl-noreward
• Owner: neka-nat
• Created: 2017-06-01T19:04:22.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2017-06-16T18:39:58.000Z (over 8 years ago)
• Last Synced: 2025-06-30T11:02:14.025Z (4 months ago)
• Topics: a3c, deep-reinforcement-learning, keras, super-mario
• Language: Python
• Homepage:
• Size: 10.8 MB
• Stars: 8
• Watchers: 2
• Forks: 4
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# async-rl-noreward

Codes are based on https://github.com/Grzego/async-rl.

Super Mario environment is used.

### Usage

To start training simply type:

```

python train.py --processes=16

```

### Requirements

* Keras

* Theano

* gym

* fceux

* ppaquette_gym_super_mario

* skimage

* h5py

* numpy