A set of RL environments for training LMs on the live web.
Project description
Web Gym
The Web as RL environments for LM training
This package contains constructs for converting the web into an RL environment where pre-trained language models can be fine-tuned via RL (PPO and other methods).
web-gym provides an interface for defining RL environments as mini-games
on the web and exposes a few built-in games such as the wikipedia navigation
game.
Development Installation
pip install .
Install ollama to run a local model: https://ollama.com/download
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 webgymnasium-0.0.0.tar.gz.
File metadata
- Download URL: webgymnasium-0.0.0.tar.gz
- Upload date:
- Size: 17.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.11.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1aa987e1f6851dbe9c556f7b686ccf9fe90f4f8df1206004e3e0f47de62214f5
|
|
| MD5 |
d22acf1382e83d7ffebe4538f6401f7d
|
|
| BLAKE2b-256 |
1dd77920ad7a4a647b1f8addd71941420c70a2b76fe7d71702126aef7a1ad236
|
File details
Details for the file webgymnasium-0.0.0-py3-none-any.whl.
File metadata
- Download URL: webgymnasium-0.0.0-py3-none-any.whl
- Upload date:
- Size: 14.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.11.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
edf45efe8e9e19209e5007397fe91996f66247d3c35597dd66b96f71f7cfdf54
|
|
| MD5 |
47ca786d0c928f2e009187a91c029c62
|
|
| BLAKE2b-256 |
493abbd5907fffea658dcd78aeacac4f321e4a053cf0b10a53b353fbc1d5404e
|
