A flexible, grid-based environment for studying decentralized, partially observable multi-agent pathfinding (PO-MAPF) problems.. No. of environments: 1

Autonomous navigation tasks with dynamic goals and obstacles, optimized using PPO.. No. of environments: 2

The Procgen Benchmark is a collection of 16 dynamic, procedurally generated environments that push the boundries of how quickly reinforcement learning agents can acquire generalizable skills in randomized scenarios.. No. of environments: 16