Didn’t DeepMind just produce a self-learning AI?
Yes, they did. MuZero was published just before Christmas 2020, and is arguably the most advanced artificial neural network based on reinforcement learning out there right now. Its predecessor, AlphaZero already had the ability to teach itself both chess and Go (another two-person zero-sum-game without random elements). AlphaZero beat world champions, but needed one important bit of information to learn:…