We used a tournament-style evaluation to demonstrate that an agent can achieve human-level performance in a 3D multiplayer first-person video game, Quake III Arena in Capture the Flag mode, using only pixels and game points scored as input. We used a 2-tier optimization process in which a population of independent RL agents are trained concurrently from 1000s of parallel matches on randomly generated environments. Each agent learns its own internal reward signal and rich representation of the world. These results indicate the great potential of multiagent reinforcement learning for artificial intelligence research.

• Uncategorized