https://github.com/openai/random-network-distillation

Code for the paper "Exploration by Random Network Distillation"
https://github.com/openai/random-network-distillation

paper

Last synced: 2 days ago
JSON representation

Code for the paper "Exploration by Random Network Distillation"

• Host: GitHub
• URL: https://github.com/openai/random-network-distillation
• Owner: openai
• Created: 2018-10-16T20:28:02.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2020-10-01T16:53:54.000Z (almost 4 years ago)
• Last Synced: 2024-09-22T10:03:23.895Z (6 days ago)
• Topics: paper
• Language: Python
• Homepage: https://openai.com/blog/reinforcement-learning-with-prediction-based-rewards/
• Size: 50.8 KB
• Stars: 873
• Watchers: 26
• Forks: 160
• Open Issues: 16
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
**Status:** Archive (code is provided as-is, no updates expected)

## [Exploration by Random Network Distillation](https://arxiv.org/abs/1810.12894) ##

Yuri Burda*, Harri Edwards*, Amos Storkey, Oleg Klimov


*equal contribution

OpenAI


University of Edinburgh

### Installation and Usage

The following command should train an RND agent on Montezuma's Revenge

```bash

python run_atari.py --gamma_ext 0.999

```

To use more than one gpu/machine, use MPI (e.g. `mpiexec -n 8 python run_atari.py --num_env 128 --gamma_ext 0.999` should use 1024 parallel environments to collect experience on an 8 gpu machine). 

### [Blog post and videos](https://blog.openai.com/reinforcement-learning-with-prediction-based-rewards/)