Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • 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

Spaces:
LostDecimal
/
alien-physics-openenv
Sleeping

App Files Files Community
Fetching metadata from the HF Docker repository...
alien-physics-openenv / scripts
35.9 kB
Ctrl+K
Ctrl+K
  • 3 contributors
History: 7 commits
LostDecimal's picture
LostDecimal
fix: GRPO zero-gradient trap, DSL prompt seed, best_reward, teacher oracle
0b77231 6 months ago
  • __init__.py
    67 Bytes
    V1 6 months ago
  • evaluate.py
    1.16 kB
    V1 6 months ago
  • generate_curriculum.py
    970 Bytes
    fix: GRPO zero-gradient trap, DSL prompt seed, best_reward, teacher oracle 6 months ago
  • grader.py
    2.91 kB
    reward curve 6 months ago
  • inference.py
    1.73 kB
    reward curve 6 months ago
  • plot_reward_curve.py
    2.63 kB
    reward curve 6 months ago
  • plot_training.py
    12.3 kB
    training results 6 months ago
  • smoke.py
    1.74 kB
    imp DSL, reward structure, paradigm shift 6 months ago
  • train_gro.py
    2.57 kB
    submodule access,timeout, gro checkpoints, mdl penalty 6 months ago
  • train_sft.py
    1.66 kB
    V1 6 months ago
  • visualize_discovery.py
    8.18 kB
    discovery plot 6 months ago