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

HarleyCooper
/
weight-space-breakout-iterative

Reinforcement Learning
Safetensors
breakout
weight-space-programming
numpy
Model card Files Files and versions
xet
Community
weight-space-breakout-iterative
504 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 8 commits
HarleyCooper's picture
HarleyCooper
Reconcile evidence, evaluation modes, historical status and dataset links; preserve weights
64a636c verified about 6 hours ago
  • experiment
    Publish verified pipeline state after 3 rounds about 18 hours ago
  • .gitattributes
    1.52 kB
    initial commit about 18 hours ago
  • LICENSE
    1.24 kB
    Publish verified pipeline state after 0 rounds about 18 hours ago
  • README.md
    7.82 kB
    Reconcile evidence, evaluation modes, historical status and dataset links; preserve weights about 6 hours ago
  • config.json
    266 Bytes
    Publish verified pipeline state after 1 rounds about 18 hours ago
  • inference.py
    1.97 kB
    Publish verified pipeline state after 0 rounds about 18 hours ago
  • initial_baseline.safetensors
    69.4 kB
    xet
    Publish verified pipeline state after 0 rounds about 18 hours ago
  • manifest.json
    31 kB
    Publish verified pipeline state after 3 rounds about 18 hours ago
  • model.safetensors
    69.4 kB
    xet
    Publish verified pipeline state after 1 rounds about 18 hours ago
  • policy.json
    8.35 kB
    Publish verified pipeline state after 1 rounds about 18 hours ago
  • policy.npz
    1.5 kB
    xet
    Publish verified pipeline state after 1 rounds about 18 hours ago