BugHuntEnvironment / inference.py

Commit History

  1. Merge remote changes and fix parse_model_action for GET payloads⁠

    dr4g0n369 +1: Claude Sonnet 4.6
    525b2ba
  2. Add GRPO training notebook and dense reward redesign for Round 2⁠

    dr4g0n369 +1: Claude Sonnet 4.6
    26e15b9

  1. Fix score formula: proportional to MAX_TASK_REWARD, clamped to (0.001, 0.999)

    2bdfabc
  2. Fix inference.py: correct stdout format and default ENV_URL to HF Space

    f1d1d6c
  3. Initial submission: Bug Hunter Env

    65ac9e6