Google’s Deepmind is working on a rather crazy and unique plan to surpass OpenAI’s biggest and best Artificial Intelligence Model within the next few months. In a new paper, AI researchers at DeepMind present a new technique to improve the capacity of reinforcement learning agents to cooperate with humans at different skill levels. Accepted at the annual NeurIPS conference, the technique is called Fictitious Co-Play (FCP) and it does not require human-generated data to train the RL agents.