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

audieleon
/
reward-failure-dataset

Reinforcement Learning
English
reward-design
reward-hacking
specification-gaming
static-analysis
safety
Model card Files Files and versions
xet
Community
reward-failure-dataset
Ctrl+K
Ctrl+K
  • 1 contributor
History: 9 commits
audieleon's picture
audieleon
Update dataset: 135 failures, 78 well-designed, fix viewer schema
8d03f68 verified 3 months ago
  • metadata
    Move croissant to metadata/ to avoid viewer conflict 3 months ago
  • .gitattributes
    1.52 kB
    initial commit 3 months ago
  • README.md
    2.85 kB
    Add dataset card with YAML config 3 months ago
  • reward_failure_dataset.csv
    56.4 kB
    Reclassify Montezuma key (CSV) 3 months ago
  • reward_failure_dataset.jsonl
    793 kB
    Update dataset: 135 failures, 78 well-designed, fix viewer schema 3 months ago