Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models
active 2024-10-11 → 2026-02-20 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 498 days from 2024-10-11 to 2026-02-20. Pushes: 3 total, peak 2 in a day. Pull requests: 2 total, peak 2 in a day. Issues: 11 total, peak 3 in a day. Comments: 20 total, peak 3 in a day. Stars: 20 total, peak 2 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 comment#13hdadong2025-04-15 04:14why you use different operator for linear velocity and angular velocity?
- Issue comment#13hdadong2025-03-28 03:39why you use different operator for linear velocity and angular velocity?
- Issue#14hdadong2025-03-28 02:40Some bugs in model inference
- Issue comment#13jake-levy2025-03-28 02:37why you use different operator for linear velocity and angular velocity?
- Issue#11hdadong2025-01-16 02:29[BUG]: The bug of model loss
- Issue comment#11hdadong2025-01-16 02:29[BUG]: The bug of model loss
- Issue#12hdadong2025-01-16 02:28When the observations are highly noisy, I encounter NaN values during world model training. Has this issue ever come up for you?
- Issue comment#10hdadong2024-11-21 02:46Why you insert the real world data into ms.sac_state.replay_buffe?
- Issue#3hdadong2024-11-21 01:25How to render test results of trained policy?
- Issue comment#9hdadong2024-10-31 12:32Have you compared the SSRL with PPO?
- Issue comment#3hdadong2024-10-30 04:46How to render test results of trained policy?
- Issue#8hdadong2024-10-28 02:28Encountered an "out of memory" error when attempting to use SSRL with my custom robot.
- Issue comment#3hdadong2024-10-28 02:28How to render test results of trained policy?
- Issue comment#8hdadong2024-10-26 01:40Encountered an "out of memory" error when attempting to use SSRL with my custom robot.
- Issue comment#8jake-levy2024-10-25 21:04Encountered an "out of memory" error when attempting to use SSRL with my custom robot.
- Issue comment#8hdadong2024-10-25 12:58Encountered an "out of memory" error when attempting to use SSRL with my custom robot.
- Issue comment#6hdadong2024-10-24 11:10MBPO Collapse and SSRL Long-Term Stability
- Issue comment#1hdadong2024-10-22 01:12Questions about random exploration in the early stages of training
- Issue#5hdadong2024-10-22 01:09Have you considered using DiffRL(based on pytorch) to implement differentiable dynamics?
- Issue comment#5hdadong2024-10-22 01:09Have you considered using DiffRL(based on pytorch) to implement differentiable dynamics?
- Issue comment#6hdadong2024-10-21 03:43MBPO Collapse and SSRL Long-Term Stability
- Issue comment#6hdadong2024-10-20 01:01MBPO Collapse and SSRL Long-Term Stability
- Issue comment#5jake-levy2024-10-19 22:30Have you considered using DiffRL(based on pytorch) to implement differentiable dynamics?
- Issue comment#6jake-levy2024-10-19 22:19MBPO Collapse and SSRL Long-Term Stability
- Pull request#7jake-levy2024-10-19 22:09
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 20 stars here means stars gained during the window, not the repo's star count.