ZJLAB-AMMI/LLM4Teach
Python code to implement LLM4Teach, a policy distillation approach for teaching reinforcement learning agents with Large Language Model
This project helps AI researchers and practitioners efficiently train specialized reinforcement learning (RL) agents for complex decision-making tasks, particularly in dynamic environments like embodied AI. It takes high-level instructions from large language models (LLMs) and uses them to guide the training of a smaller, more specialized RL agent. The outcome is an RL agent that learns faster with less data and can outperform the initial LLM guidance.
No commits in the last 6 months.
Use this if you are an AI researcher or developer working on reinforcement learning tasks and want to leverage the broad knowledge of LLMs to train more efficient and specialized RL agents.
Not ideal if you are looking for a plug-and-play LLM solution for general decision-making without needing to train a specialized agent.
Stars
53
Forks
16
Language
Python
License
—
Category
Last pushed
Apr 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ZJLAB-AMMI/LLM4Teach"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
agentscope-ai/Trinity-RFT
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement...
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO &...
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
huggingface/alignment-handbook
Robust recipes to align language models with human and AI preferences
hyunwoongko/nanoRLHF
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.