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.
–
TIMESTAMPS:
00:00 How Deepmind is ahead of OpenAI
01:45 Why this AI is similar to our Brain.
04:17 New AI Features and Abilities.
06:36 How successful was this AI?
08:58 The Future of AI
10:13 Last Words.
–
#ai #agi #deepmind