![]() ![]() “In order to learn how to play tactically and collaborate with their teammates, these agents must rely on feedback from the game outcomes - without any teacher or coach showing them what to do.” “What makes these results so exciting is that these agents perceive their environment from a first-person perspective, just as a human player would,” DeepMind research scientist Thore Graepel said in a statement. This resulted in “decentralized control within a team” of AI agents, according to the paper. Instead, they learned independently from pixel data and a game score. Illustration of AI agents playing 'Quake III Arena.' Credit: DeepMindĬrucially, the AI agents in DeepMind’s Quake III Arena study had no access to game information that a human player wouldn’t, and didn’t learn from each other.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |