Commit History

23 days ago

  1. Final agent GRPO main; mean_reward=0.100

    Verified signature
    48be033
  2. TRL: inject text/JSON tool calls + forced ls into tool loop

    Verified signature
    c658700
  3. Force first tool + tool_choice required nudge

    Verified signature
    0ecc38b
  4. Shaped rewards + root listing in reset

    Verified signature
    8e4528c
  5. Fix Langfuse ckpt/heldout child trace_context

    Verified signature
    d5f40a1
  6. Fix Langfuse: clean roots + explicit child parents

    Verified signature
    8b908da
  7. Ultra-detailed agent prompt

    Verified signature
    721e233
  8. Reset tip edge cases

    Verified signature
    5e41a53
  9. Smoke mode + detailed train entry

    Verified signature
    e1bfc06
  10. Add deepagents_rl package sources

    Verified signature
    47f9048
  11. Add kaggle/train_grpo.py

    Verified signature
    dfbd12e
  12. Add deepagents_rl package sources

    Verified signature
    176c299
  13. ls fallback: no assume src/

    Verified signature
    91d2777
  14. ls fallback: no assume src/

    Verified signature
    59a0ac5
  15. Add kaggle/train_grpo.py

    Verified signature
    681342c
  16. Add deepagents_rl package sources

    Verified signature
    2c121ec
  17. Add kaggle/train_grpo.py

    Verified signature
    147b723
  18. Add kaggle/train_grpo.py

    Verified signature
    4b87130
  19. Add kaggle/train_grpo.py

    Verified signature
    f5cb9ca
  20. Add deepagents_rl package sources

    Verified signature
    8dd7dcc
  21. Add kaggle/train_grpo.py

    Verified signature
    a48afd7
  22. Add deepagents_rl package sources

    Verified signature
    e819bd7
  23. Add kaggle/train_grpo.py

    Verified signature
    488f5fc
  24. Add deepagents_rl package sources

    Verified signature
    8cf91b5
  25. Add kaggle/train_grpo.py

    Verified signature
    deddf9f
  26. Add deepagents_rl package sources

    Verified signature
    82c54e4
  27. Add kaggle/KAGGLE_SETUP.md

    Verified signature
    d91c758
  28. Add kaggle/train_grpo.py

    Verified signature
    7ca973d
  29. Add kaggle/train_grpo.py

    Verified signature
    5ee5b9f
  30. Add deepagents_rl package sources

    Verified signature
    4d620d9
  31. Add README.md

    Verified signature
    a0141b0
  32. Add configs/kaggle_grpo.yaml

    Verified signature
    0feee97
  33. Add kaggle/KAGGLE_SETUP.md

    Verified signature
    29c1d2c
  34. Add kaggle/train_grpo.py

    Verified signature
    aa44576
  35. Add kaggle/KAGGLE_SETUP.md

    Verified signature
    a5b37a7
  36. Add kaggle/train_grpo.py

    Verified signature
    a4f498d
  37. Add kaggle/KAGGLE_SETUP.md

    Verified signature
    1995803
  38. Add kaggle/train_grpo.py

    Verified signature
    4a87f27
  39. Add kaggle/train_grpo.py

    Verified signature
    eb61e79
  40. Add deepagents_rl package sources

    Verified signature
    a31a731
  41. Add README.md

    Verified signature
    af71b36
  42. Add configs/kaggle_grpo.yaml

    Verified signature
    0611681
  43. Add kaggle/KAGGLE_SETUP.md

    Verified signature
    bec7374
  44. Add kaggle/train_grpo.py

    Verified signature
    a54bfe0
  45. initial commit

    Verified signature
    8b492f7