Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

zimmerk4
/
getting-over-it-rl-jax

Reinforcement Learning
JAX
ppo
sim-to-real
getting-over-it
Model card Files Files and versions
xet
Community
getting-over-it-rl-jax
11.7 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
zimmerk4's picture
zimmerk4
Network as npz only (config embedded, no pickle); command and logs of the 20 real-game climbs
7583dbf verified 21 days ago
  • eval
    Network as npz only (config embedded, no pickle); command and logs of the 20 real-game climbs 21 days ago
  • media
    Winning policy, checkpoint, model card and clip 21 days ago
  • .gitattributes
    1.69 kB
    Winning policy, checkpoint, model card and clip 21 days ago
  • README.md
    4.37 kB
    Network as npz only (config embedded, no pickle); command and logs of the 20 real-game climbs 21 days ago
  • config.json
    1.61 kB
    Winning policy, checkpoint, model card and clip 21 days ago
  • policy.npz
    758 kB
    xet
    Network as npz only (config embedded, no pickle); command and logs of the 20 real-game climbs 21 days ago