Nikunj-Gupta/conformal-agent-modelling

CAMMARL: Conformal Action Modeling in Multi Agent Reinforcement Learning

19
/ 100
Experimental

This project helps autonomous agents in multi-agent environments make better decisions by understanding what other agents might do. It takes observations from the environment and uses them to predict a "confident set" of actions that other agents are likely to take, along with a probability of those actions. This helps the agent choose its own actions more effectively, especially in cooperative tasks like coordinating movement or foraging. It's designed for researchers and engineers working on advanced multi-agent reinforcement learning systems.

No commits in the last 6 months.

Use this if you are developing autonomous agents in multi-agent environments and need a way for your agents to model the uncertain behavior of other agents with quantifiable confidence.

Not ideal if you are looking for a pre-trained, ready-to-deploy solution for a specific real-world multi-agent problem, as this is a research-focused algorithm implementation.

multi-agent-systems reinforcement-learning autonomous-decision-making predictive-modeling cooperative-ai
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

15

Forks

1

Language

Python

License

Last pushed

Jun 24, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Nikunj-Gupta/conformal-agent-modelling"

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