Skip to main content

LocoFormer

Project description

LocoFormer (wip)

LocoFormer - Generalist Locomotion via Long-Context Adaptation

The gist is they trained a simple Transformer-XL in simulation on robots with many different bodies (cross-embodiment). When transferring to the real-world, they noticed the robot now gains the ability to adapt to insults. The XL memories span across multiple trials, which allowed the robot to learn in-context adaptation.

Sponsors

This open sourced work is sponsored by Safe Sentinel

Citations

@article{liu2025locoformer,
    title   = {LocoFormer: Generalist Locomotion via Long-Context Adaptation},
    author  = {Liu, Min and Pathak, Deepak and Agarwal, Ananye},
    journal = {Conference on Robot Learning ({CoRL})},
    year    = {2025}
}

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

locoformer-0.0.2.tar.gz (36.9 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

locoformer-0.0.2-py3-none-any.whl (6.1 kB view details)

Uploaded Python 3

File details

Details for the file locoformer-0.0.2.tar.gz.

File metadata

  • Download URL: locoformer-0.0.2.tar.gz
  • Upload date:
  • Size: 36.9 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.25

File hashes

Hashes for locoformer-0.0.2.tar.gz
Algorithm Hash digest
SHA256 1fc04a46a3839bbbb3fbba42048c0b2ec34d1ba7f7cea9bf5b38c6c8b1024305
MD5 9aef3f1d9d77c23ee2ead7355915ddc9
BLAKE2b-256 beefb962580f59d821428bda0795a7d141d967f6267e557d7daa8eb384e5f82f

See more details on using hashes here.

File details

Details for the file locoformer-0.0.2-py3-none-any.whl.

File metadata

  • Download URL: locoformer-0.0.2-py3-none-any.whl
  • Upload date:
  • Size: 6.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.25

File hashes

Hashes for locoformer-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 046d9a6f077791e02851ddda11b5b9677e665ef102af67129be97813230f99f8
MD5 50f3a328814ee88ac5d7f1f4be5e3107
BLAKE2b-256 6f374c26a2d4e3dfc90e095c22b5b3d7207be8ccfd2d150aa813a9beafd4fb78

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page