Standard Multi-Agent Reinforcement Learning (MARL) methods usually concentrate on the self-play (SP) setting where the strategies are being constructed by playing the game with themselves repeatedly. However, there may occur an error in some cases such as autonomous driving cars, cooperative game playing, among others.  Applying the Self-Play method to zero-shot coordination problem can produce…

The post After Apple, Facebook Unveiled It’s Enhanced Self-Play Algorithm For Autonomous Cars appeared first on Analytics India Magazine.