Nothing Special   »   [go: up one dir, main page]

×
Please click here if you are not redirected within a few seconds.
Nov 18, 2017 · We propose the first concrete and domain-general learning algorithm for approximating the optimal selection of computations: Bayesian metalevel policy search ( ...
The human mind circumvents this computational challenge by learning to select computations through metacognitive reinforcement learning (Krueger, Lieder,. & ...
The efficient use of limited computational resources is an essential ingredient of intelligence. Selecting computations optimally according to rational ...
Inspired by psychology and neuroscience, we propose the first concrete and domain-general learning algorithm for approximating the optimal selection of ...
We derive a general, sample-efficient reinforcement learning algorithm for learning to select computations from the insight that the value of computation lies ...
We are interested in autonomous learning, that is how an embodied agent can determine what to learn, how to learn, and how to judge the learning success.
Nov 18, 2017 · The basic idea is that the decision-making process can be broken down into a series of computations that update the decision maker's beliefs ...
In essence, computations can be selected according to the expected improvement in decision quality resulting from their execution. I. J.
The blinkered policy of Hay et al. (2012) was defined for problems where each computation informs the value of only one action.
Computational learning theory (or just learning theory) is a subfield of artificial intelligence devoted to studying the design and analysis of machine ...