AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Are You Using Self Supervised Learning to Make Things More Efficient?
I see self supervisring as as a preliminary to all of the above. To learn to play at harry games take about 80 hours of training to reach the level that any human can reach in about 15 minutes. They get better than humans, but it takes them a long time. Alfastar ok te, you know arriol vinas an, and is teams e system to play, to to play stock craft plays with about the eqivalment of 200 years of training, playing against itself. The e quickly explodes, what are your thoughts? And the extension of this, which topic i'm super excited about. Its connected to something you are talking about in terms of rabotics