Hugging Face's logo

mathisweil
/
remdm-minihack-checkpoints

Reinforcement Learning
PyTorch
Safetensors
planning
discrete-diffusion
remdm
minihack
nethack
Model card Files
xet
 Community
remdm-minihack-checkpoints

Commit History

11 days ago

  1. Cite the paper with all five authors and link OpenReview

    mathisweil
    Verified signature
    da1602b

  1. Upload MiniHack ReMDM planner checkpoints and results

    mathisweil
    Verified signature
    c6bec21

  2. Upload MiniHack ReMDM planner checkpoints and results

    mathisweil
    Verified signature
    bb916bf

  3. Upload MiniHack ReMDM planner checkpoints and results

    mathisweil
    Verified signature
    1b7f2b1

  1. refresh flattened ablation tables from the new run

    mathisweil
    Verified signature
    eea93e7

  2. refresh flattened ablation tables from the new run

    mathisweil
    Verified signature
    4b4923e

  3. refresh flattened ablation tables from the new run

    mathisweil
    Verified signature
    8385a0c

  4. refresh flattened ablation tables from the new run

    mathisweil
    Verified signature
    0703b4c

  5. refresh flattened ablation tables from the new run

    mathisweil
    Verified signature
    bfde26f

  6. refresh flattened ablation tables from the new run

    mathisweil
    Verified signature
    ef39129

  7. refresh flattened ablation tables from the new run

    mathisweil
    Verified signature
    c9c5c64

  8. Upload MiniHack ReMDM planner checkpoints and results

    mathisweil
    Verified signature
    3ff1ac8

  9. remove superseded release: experiments/rl_finetuning/outputs/minihack_ablations

    mathisweil
    Verified signature
    6955e3f

  10. remove superseded release: checkpoints/online/Minihack-Online-Diffusion-DAgger-100M

    mathisweil
    Verified signature
    92284b5

  11. remove superseded release: checkpoints/offline/Minihack-Offline-Diffusion-BC-100M

    mathisweil
    Verified signature
    c12cc22

  1. cleanup: remove temporary tmp-inference-pm4p9re8

    mathisweil
    Verified signature
    8aa9f60

  2. cleanup: remove temporary tmp-ablations-24of25-run_20260820_002747

    mathisweil
    Verified signature
    c6ff65c

  3. cleanup: remove temporary tmp-ablations-25of25

    mathisweil
    Verified signature
    a8d87a7

  4. Temporary: inference on pm4p9re8/iter563 (the 25-ablation baseline checkpoint)

    mathisweil
    Verified signature
    69eeaa9

  5. Temporary: MiniHack ablation suite, complete 25 of 25

    mathisweil
    Verified signature
    718a745

  1. Temporary: MiniHack ablation suite, 24 of 25 (3090 Ti run, reward_model missing)

    mathisweil
    Verified signature
    e9074a6

  1. Upload MiniHack ReMDM planner checkpoints and results

    mathisweil
    Verified signature
    a7a1c23

  2. Delete checkpoints/online/Minihack-OnlineDiffusion-DAgger-123M

    mathisweil
    Verified signature
    6d421b9

  3. Delete checkpoints/online/Minihack-Online-Diffusion-DAgger-6M

    mathisweil
    Verified signature
    4b69729

  4. Delete checkpoints/offline/Minihack-OfflineDiffusion-BC-82M

    mathisweil
    Verified signature
    cd7aea7

  5. Delete checkpoints/iter10.pth

    mathisweil
    Verified signature
    2456efd

  6. Delete checkpoints/iter11.pth

    mathisweil
    Verified signature
    b4853d4

  7. Delete checkpoints/iter5.pth

    mathisweil
    Verified signature
    ea799bd

  8. Delete .gitattributes

    mathisweil
    Verified signature
    cd13f56

  9. Delete checkpoints/model.safetensors

    mathisweil
    Verified signature
    7c9fb26

  10. Delete checkpoints/config_iter5.yaml

    mathisweil
    Verified signature
    7dd398f

  11. Delete checkpoints/config_iter11.yaml

    mathisweil
    Verified signature
    8a48fcf

  12. Delete checkpoints/selection.json

    mathisweil
    Verified signature
    55f3ca8

  13. Delete checkpoints/config_iter10.yaml

    mathisweil
    Verified signature
    ad559ac

  1. Upload MiniHack ReMDM planner checkpoints and results

    mathisweil
    Verified signature
    ea679b7

  2. Upload MiniHack ReMDM planner checkpoints

    mathisweil
    Verified signature
    7688292

  3. Upload MiniHack ReMDM planner checkpoints

    mathisweil
    Verified signature
    42ac343

  4. Upload MiniHack ReMDM planner checkpoints

    mathisweil
    Verified signature
    f3010d9

  5. Upload MiniHack ReMDM planner checkpoints

    mathisweil
    Verified signature
    b502fdb

  1. Upload MiniHack ReMDM planner checkpoints

    Mathis Weil
    Verified signature
    ffced82

  2. initial commit

    Mathis Weil
    Verified signature
    27912b6