Metadata-Version: 2.1
Name: l3c
Version: 0.1.1.1
Summary: L3C provide abundant environments for Lifelong Learning (L3) in Context.
Home-page: https://github.com/FutureAGI/L3C
Author: WorldEditors
Author-email: 
License: Apache
Platform: UNKNOWN
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Requires-Dist: gym (>=0.18.0)
Requires-Dist: numpy (>=1.16.4)
Requires-Dist: Pillow (>=6.2.2)
Requires-Dist: six (>=1.12.0)
Requires-Dist: pygame (>=2.0.2dev2)
Requires-Dist: numba (>=0.55.0)

# L3C

L3C provides variant environments facilitating In-Context Learning, featured in the following assets:
- Minimal knowledge transferrable among huge amounts of tasks
- Lifelong In-Context Learning
- Generative and Interactive

# Environments Updating

- [MazeWorlds](l3c/mazeworld): 2D/3D maze generators for task generalization

- [MetaLanguage](l3c/metalang): Pseudo-language generated from randomized hyper-parameters

- [Bandits](l3c/bandits): Bandits task generalization

- [L3C_Baselines](https://github.com/FutureAGI/L3C_Baselines): An implementation of the baseline solutions to the above tasks

# Installation

```bash
pip install l3c
```


