LLAMP - Large Language Model for Planning
Project description
# LLamp - Large Languge Models for Planning
This is a package that uses LLMs (closed and open-source) for planning.
**WARNING PACKAGE IS STILL UNDER DEVELOPMENT and requirements needs cleaning up.**
## Installation:
1. Textworld Game (pip install textworld)
2. Textworld Visualisation (pip install -r requirements_textworld_visualisation.txt)
3. (install chromedriver or firefox driver)
## Generate New Textworld games:
1. `tw-make custom --world-size 2 --nb-objects 10 --quest-length 5 --seed 1234 --output tw_games/w2_o10_l5_game.z8`
## Playgame:
1. (In terminal with browser visualiser) `tw-play tw_games/first_game.z8 --viewer`
2. (as Gym environement in terminal) `python3 playground_tw_gym.py`
### Available Commands to agent:
```bash
Available commands:
look: describe the current room
goal: print the goal of this game
inventory: print player's inventory
go <dir>: move the player north, east, south or west
examine ...: examine something more closely
eat ...: eat edible food
open ...: open a door or a container
close ...: close a door or a container
drop ...: drop an object on the floor
take ...: take an object that is on the floor
put ... on ...: place an object on a supporter
take ... from ...: take an object from a container or a supporter
insert ... into ...: place an object into a container
lock ... with ...: lock a door or a container with a key
unlock ... with ...: unlock a door or a container with a key
```
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
llamp-0.0.2.tar.gz
(1.8 kB
view details)
File details
Details for the file llamp-0.0.2.tar.gz
.
File metadata
- Download URL: llamp-0.0.2.tar.gz
- Upload date:
- Size: 1.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | d6b71706a88f006a6e40edc9b202f2d70a7869895f16cfaed7541cbe650165ab |
|
MD5 | 307a788221c7cabc192a7db41fe99f97 |
|
BLAKE2b-256 | 9c8e4c27595fa9a0077019f381b1b6570d9495ee66f581964ba060a12b641633 |