Gaussian processes (GPs) produce good probabilistic models of functions,...
Algorithmic Information Theory has inspired intractable constructions of...
In imitation learning, imitators and demonstrators are policies for pick...
If we could define the set of all bad outcomes, we could hard-code an ag...
Reinforcement learners are agents that learn to pick actions that lead t...
General intelligence, the ability to solve arbitrary solvable problems, ...
Reinforcement Learning agents are expected to eventually perform well.
T...