IanRDavies/LeMOL
Experimenting with meta-learning approaches to opponent modelling in MARL. Building upon previous public implementations of MADDPG and M3DDPG.
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.
Stars
14
Forks
4
Language
Python
License
AGPL-3.0
Category
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.
Higher-rated alternatives
Toni-SM/skrl
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with...
facebookresearch/BenchMARL
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL...
utiasDSL/gym-pybullet-drones
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
datamllab/rlcard
Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
gtri/scrimmage
Multi-Agent Robotics Simulator