QuantHive / training

Commit History

  1. Semantic observation prompts — rich text replaces raw floats (judge feedback #1)

    213c699

  1. Update latest changes

    aec0295
  2. Update training notebook and verifiers

    a3c00eb
  3. fix(notebook): correct clone step order, extract prompt utils, fix github url

    30a586b
  4. Hackathon Final Submission: PettingZoo multi-agent arch, GRPO training, docs

    9cb3002