IanRDavies/LeMOL

Experimenting with meta-learning approaches to opponent modelling in MARL. Building upon previous public implementations of MADDPG and M3DDPG.

36
/ 100
Emerging

This project helps researchers and engineers in multi-agent systems to better predict and adapt to the strategies of other agents in a shared environment. By inputting multi-agent interaction data, it generates models that can anticipate how opponents will learn and behave. It is designed for practitioners working with competitive or collaborative AI in simulated environments.

No commits in the last 6 months.

Use this if you are developing AI agents for simulations like particle environments or UAV control and need a sophisticated method for your agents to model and respond to opponents' evolving strategies.

Not ideal if you are looking for a solution for real-world, highly complex multi-agent scenarios outside of simulation, or if you need to model more than two interacting agents.

multi-agent-systems opponent-modelling reinforcement-learning game-theory simulated-environments
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

14

Forks

4

Language

Python

License

AGPL-3.0

Last pushed

Apr 26, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/IanRDavies/LeMOL"

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