Skip to content

Official code for "QueST: Self-Supervised Skill Abstractions for Continuous Control" [NeurIPS 2024]

active 2024-09-152026-03-03 (UTC)

Partial coverage14,308 / 17,288 hourly files (83%) · 2 absent upstream · 2,979 failed, retryable2024-08-212026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
136
Pushes
2
Pull requests
4
Issues
14
Stars
69
Forks
6

Activity over time

Daily event counts in the loaded window

Line chart, 535 days from 2024-09-15 to 2026-03-03. Pushes: 2 total, peak 2 in a day. Pull requests: 4 total, peak 4 in a day. Issues: 14 total, peak 3 in a day. Comments: 34 total, peak 6 in a day. Stars: 69 total, peak 5 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue#28SMLee04072025-11-25 08:01
    Data preprocessing for Libero
  • Issue#27jayaramreddy102025-10-15 13:18
    Unable to Replicate Results of Fig. 3a and Fig. 3b (for MetaWorld benchmark)
  • Issue comment#21jayaramreddy102025-10-15 12:17
    Meta-World Reproduction Issue
  • Issue comment#24Kalcy-U2025-09-17 11:52
    Action reconstruction of skill vae
  • Issue#26EmbodiedMind2025-09-07 08:55
    MetaWorld version mismatch: v2 symbols required (`ALL_V2_ENVIRONMENTS_GOAL_OBSERVABLE`), PyPI provides v3
  • Issue comment#24OrangeSodahub2025-08-12 11:44
    Action reconstruction of skill vae
  • Issue comment#24OrangeSodahub2025-08-11 07:11
    Action reconstruction of skill vae
  • Issue comment#25atharvamete2025-08-10 20:22
    Error locating target ‘quest.utils.libero_utils.build_dataset’.
  • Issue comment#24atharvamete2025-08-10 20:17
    Action reconstruction of skill vae
  • Issue comment#24OrangeSodahub2025-08-10 18:45
    Action reconstruction of skill vae
  • Issue comment#24OrangeSodahub2025-08-05 14:26
    Action reconstruction of skill vae
  • Issue comment#23OrangeSodahub2025-07-22 20:36
    How to upsample when decoding actions
  • Issue comment#5Triumphant-strain2025-06-18 11:54
    train_error
  • Issue#22Jasper-aaa2025-03-02 04:08
    Evaluation problem: Video saving
  • Issue#12atharvamete2024-11-24 02:20
    Few-shot unseen task setting
  • Issue#14atharvamete2024-11-24 02:20
    Why does the grad-norm saturate in Stage-2 ?
  • Issue comment#15atharvamete2024-11-24 02:19
    Configuration Action Chunk Size and other relevant paremers
  • Issue#8atharvamete2024-11-21 02:59
    `./scripts/dp/main.sh` not working
  • Issue comment#12jis36132024-11-21 01:38
    Few-shot unseen task setting
  • Issue comment#14jis36132024-11-21 01:22
    Why does the grad-norm saturate in Stage-2 ?
  • Issue comment#8atharvamete2024-11-20 02:23
    `./scripts/dp/main.sh` not working
  • Issue comment#12atharvamete2024-11-20 02:11
    Few-shot unseen task setting
  • Issue comment#14atharvamete2024-11-20 02:09
    Why does the grad-norm saturate in Stage-2 ?
  • Issue comment#13atharvamete2024-11-20 02:05
    question about stage-1 training
  • Issue#11MK-D-Luffy2024-11-09 05:00
    Question about checkpoint loading

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 69 stars here means stars gained during the window, not the repo's star count.