Data

Tools

Indexes

Applications

Experiments

Open Source Science

megastep

megastep helps you build 1-million FPS reinforcement learning environments on a single GPU

https://github.com/andyljones/megastep

Science Score: 18.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (3.2%) to scientific vocabulary

Keywords

machine-learning reinforcement-learning
Last synced: 10 months ago · JSON representation ·

Repository

megastep helps you build 1-million FPS reinforcement learning environments on a single GPU

Basic Info
Statistics
  • Stars: 140
  • Watchers: 2
  • Forks: 12
  • Open Issues: 3
  • Releases: 0
Topics
machine-learning reinforcement-learning
Created about 6 years ago · Last pushed over 4 years ago
Metadata Files
Readme License Citation

README.md

megastep

Documentation Status Discord

megastep helps you build 1-million FPS reinforcement learning environments with a single consumer GPU.

Docs, tutorials and more are available on the project homepage.

Owner

  • Name: Andy Jones
  • Login: andyljones
  • Kind: user
  • Location: London
  • Company: Anthropic

engineer/researcher

Citation (CITATION) 

@software{megastep,
  author = {{Andy L Jones}},
  title = {megastep},
  url = {https://andyljones.com/megastep},
  version = {0.1},
  date = {2020-07-07},
}

GitHub Events

Total
  • Watch event: 6
  • Fork event: 1
Last Year
  • Watch event: 6
  • Fork event: 1

Dependencies

setup.py pypi
  • matplotlib >=3
  • ninja >=1.10
  • numpy >=1.18
  • torch >=1.5
  • torchvision >=0.6
  • tqdm >=4