Re:USN AN-1 Submarine Aircraft Carrier (2018)
by b3kart on Thursday January 21, 2021 @11:49AM
(#25860952)
> if lessons are learned
This is the key statement. Even in reinforcement learning exploring intelligently is an important problem. There’s no point exploring a new state if your world model is confident about what’s going to happen there: you won’t learn much.
This is the key statement. Even in reinforcement learning exploring intelligently is an important problem. There’s no point exploring a new state if your world model is confident about what’s going to happen there: you won’t learn much.