CharlieBrown-v1/KALM
[NeurIPS'24] KALM: Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts
This project helps AI researchers train better robotic agents by leveraging the extensive knowledge of Large Language Models (LLMs). It takes existing offline reinforcement learning datasets and an LLM, then generates enriched 'imaginary' data to train robotic policies that can perform complex tasks more effectively. The primary user would be an AI/ML researcher or practitioner focused on robotics and decision-making systems.
No commits in the last 6 months.
Use this if you are an AI researcher looking to enhance the performance of your robotic agents by incorporating knowledge from large language models without needing online interaction.
Not ideal if you are looking for a plug-and-play solution for real-world robot deployment or if you lack expertise in machine learning and reinforcement learning.
Stars
9
Forks
4
Language
Python
License
—
Category
Last pushed
Oct 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/CharlieBrown-v1/KALM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
xrsrke/toolformer
Implementation of Toolformer: Language Models Can Teach Themselves to Use Tools
MozerWang/AMPO
[ICLR 2026] Adaptive Social Learning via Mode Policy Optimization for Language Agents
real-stanford/reflect
[CoRL 2023] REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction
nsidn98/LLaMAR
Code for our paper LLaMAR: LM-based Long-Horizon Planner for Multi-Agent Robotics
BatsResearch/planetarium
Dataset and benchmark for assessing LLMs in translating natural language descriptions of...