ZJLAB-AMMI/LLM4RL

A RL approach to enable cost-effective, intelligent interactions between a local agent and a remote LLM

33
/ 100
Emerging

This project helps operations engineers and researchers studying autonomous agents to manage how an agent interacts with large language models (LLMs). It takes in an agent's task objectives and its environment, and outputs a strategy that significantly reduces the cost and time spent communicating with remote LLMs, while maintaining task performance. This is for anyone building or experimenting with AI agents in environments like robotics or simulation that need to make decisions efficiently.

No commits in the last 6 months.

Use this if you are developing or testing autonomous agents that rely on LLMs for high-level guidance and want to make those interactions more cost-effective and faster.

Not ideal if your agent operates in environments where LLM interaction costs are not a concern, or if you are not using LLMs for task planning.

autonomous-agents robotics AI-efficiency decision-making agent-simulation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

79

Forks

13

Language

Python

License

Last pushed

Aug 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/ZJLAB-AMMI/LLM4RL"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.