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-0.0.3.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-0.0.3-py3-none-any.whl (6.4 kB view details)

Uploaded Python 3

File details

Details for the file locoformer-0.0.3.tar.gz.

File metadata

  • Download URL: locoformer-0.0.3.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-0.0.3.tar.gz
Algorithm Hash digest
SHA256 02de83f3bb42abe31d0ddb2ea87f7ac47732d46a1ab174e84fd67fa28cfb395a
MD5 0a3e4f4be750912a65dada665730a97d
BLAKE2b-256 72742b77619cdf40c9f7126097345e1366c2d7776d0d0b69be36b469bd5aa260

See more details on using hashes here.

File details

Details for the file locoformer-0.0.3-py3-none-any.whl.

File metadata

  • Download URL: locoformer-0.0.3-py3-none-any.whl
  • Upload date:
  • Size: 6.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.25

File hashes

Hashes for locoformer-0.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 4e92e8bcb0df94a039d196a8c77361349ed6bda7d122e8792a66299848c50acf
MD5 a1b8a00b8bdef504fb88bc05c9be707a
BLAKE2b-256 a194b48e5d3f4d6f1e6954f069c658e623f27593f1824e76048a7c313493f584

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