Recently, a team of researchers from Microsoft Research, UC Berkeley and the University of Nottingham has developed a new methodology for testing the human-AI collaboration of reinforcement learning (RL) agents using a two-player game environment, Overcooked. In this environment, the players control chefs in a kitchen to cook and serve dishes.  First, the researchers made…

The post What’s Cooking? After Poker and Go, Researchers Use New Game To Evaluate RL Agents’ Robustness appeared first on Analytics India Magazine.