keskival/embodied-emulated-personas
A project space for Embodied Emulated Personas - Embodied neural networks trained by LLM chatbot teachers
This project helps AI researchers create more capable artificial agents by extracting personality and behavior from large language models (LLMs) and imbuing them into physically-aware agents. It takes the textual descriptions of scenarios and actions generated by an LLM-driven persona and uses them to train a separate neural network that directly controls a virtual body. AI researchers working on embodied AI, robotics, or agent development would find this useful for developing agents that behave according to complex, human-like personas.
No commits in the last 6 months.
Use this if you want to give a virtual or physical AI agent a consistent 'personality' and decision-making style based on an LLM's emulated persona, moving beyond just text-based interactions.
Not ideal if your primary goal is optimizing for task-specific performance rather than replicating a specific behavioral policy or persona, as this focuses on imitation learning from an LLM teacher.
Stars
16
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 30, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/keskival/embodied-emulated-personas"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AMA-CMFAI/LAMBDA
This is the offical repository of paper "LAMBDA: A large Model Based Data Agent"....
zjunlp/LLMAgentPapers
Must-read Papers on LLM Agents.
hyp1231/awesome-llm-powered-agent
Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...
MineDojo/Voyager
An Open-Ended Embodied Agent with Large Language Models
InfiXAI/InfiGUI-G1
[AAAI 2026 Oral] Official repository for InfiGUI-G1. We introduce Adaptive Exploration Policy...