Meta-Optimization Using Sequential Experiences — core ICRL library
Project description
Meta-Optimization Using Sequential Experiences
MOUSE is a modular PyTorch library for in-context reinforcement learning. It provides the building blocks — embeddings, transformer backbones, output heads, losses, and data utilities — for training and deploying agents that adapt their behaviour by attending over their own transition history, with no weight updates at inference time.
Install
pip install "git+https://github.com/micahr234/mouse-core.git"
Documentation
📖 micahr234.github.io/mouse-core
Contributing
Contributions are welcome — see CONTRIBUTING.md.
License
GNU General Public License v3.0 — see LICENSE.
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
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mouse_core-0.1.0.tar.gz.
File metadata
- Download URL: mouse_core-0.1.0.tar.gz
- Upload date:
- Size: 57.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
abedb88369bbd7edfbbfd49944c782c07e2e1999da0f71a20b9c4c2b3ae8736e
|
|
| MD5 |
8e41dfb56082889e872ef830c42d2cad
|
|
| BLAKE2b-256 |
3cd3662e1ca126db30b90bb019740536ab7a91c07495b72a9c42c12355fc990b
|
File details
Details for the file mouse_core-0.1.0-py3-none-any.whl.
File metadata
- Download URL: mouse_core-0.1.0-py3-none-any.whl
- Upload date:
- Size: 70.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
33760e0dd4b6cd921679e83d1dba92558680d14a191cb70c39385ecee2865d92
|
|
| MD5 |
68198a5f8bdd499a60683761678c7f32
|
|
| BLAKE2b-256 |
7568d4b07962902a080d1b801f0ea13dfa889d337c9df0245314beef2aaf4352
|
