L3C provide abundant environments for Lifelong Learning (L3) in Context.
Project description
L3C
L3C provides variant environments facilitating In-Context Learning, featured in the following assets:
- Vast amounts of diversified tasks with minimal inductive bias
- Lifelong In-Context Learning
- Generative and Interactive
Environments Updating
-
MazeWorld: 2D/3D maze generators for task generalization
-
MetaLanguage: Pseudo-language generated from randomized hyper-parameters
-
Bandits: Bandits task generalization
-
L3C_Baselines: An implementation of the baseline solutions to the above tasks
Installation
pip install l3c
Reference
Cite this work with
@article{wang2024benchmarking,
title={Benchmarking General Purpose In-Context Learning},
author={Wang, Fan and Lin, Chuan and Cao, Yang and Kang, Yu},
journal={arXiv preprint arXiv:2405.17234},
year={2024}
}
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
l3c-0.1.1.2.tar.gz
(30.9 kB
view hashes)
Built Distribution
l3c-0.1.1.2-py2.py3-none-any.whl
(99.1 kB
view hashes)
Close
Hashes for l3c-0.1.1.2-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | abd33f766e9fb2e2e06fb7c8b0f0fe3f006e5d5f77fd3fe59c67130adcaad668 |
|
MD5 | 2934f72a98e28081d2b5aefc7e0ab8b6 |
|
BLAKE2b-256 | 177b5fd3776cae692702081870c8332b585290b2b2927c07962681148aa9167c |