PRIMAL
What it is
PRIMAL is a distributed Reinforcement Learning (RL) and Imitation Learning (IL) framework designed for Multi-Agent Path Finding (MAPF). It trains multiple agents to cooperatively navigate 2D grid worlds and provides tools for systematic validation and visualization.
The problem it solves
Solving complex multi-agent pathfinding (MAPF) where agents must coordinate to avoid collisions and reach goals efficiently.
What you could use it for
- Training multi-agent pathfinding models in 2D grid environments
- Simulating collaborative path planning with obstacles and multiple goals
- Evaluating pathfinding policies across various handcrafted scenarios
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.