princeton-nlp/lwm
We develop world models that can be adapted with natural language. Intergrating these models into artificial agents allows humans to effectively control these agents through verbal communication.
This project helps AI developers build artificial agents that can be controlled and understand their environment using natural language instructions. By providing language descriptions and observing how an agent interacts within a simulated environment, developers can train a 'world model' that predicts outcomes. This model then allows for more effective policy learning to guide the agent's actions.
No commits in the last 6 months.
Use this if you are developing AI agents for environments where natural language commands are crucial for control and understanding.
Not ideal if your AI application doesn't involve complex simulated environments or requires control solely through non-linguistic inputs.
Stars
25
Forks
3
Language
Python
License
GPL-3.0
Category
Last pushed
Feb 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/princeton-nlp/lwm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
web-arena-x/webarena
Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"
nabeelxy/syara
SYARA: Super YARA Rules for GenAI Era
princeton-nlp/WebShop
[NeurIPS 2022] đź›’WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
X-LANCE/Mobile-Env
A Universal Platform for Training and Evaluation of Mobile Interaction
shbernal/pdfanki
Create Anki decks from PDF/EPUB files using NLP with LLMs.