Speaker
Alexey A. Melnikov
(Institute for Theoretical Physics, University of Innsbruck)
Description
The projective simulation (PS) model is a physical approach to artificial intelligence. In the PS model, learning is realized by internal modification of the episodic memory network, both in terms of its structure and the weights of its edges. Through interactions with a task environment, the PS memory network adjusts itself dynamically, so as to increase the probability of performing better in subsequent time steps. Here we consider several examples of environments, in which the PS agent does self-adjustments due to glow, generalization and meta-learning mechanisms. The emphasis is made on examples of the PS agent applied to quantum optics experiments.
Author
Alexey A. Melnikov
(Institute for Theoretical Physics, University of Innsbruck)
Co-authors
Dr
Vedran Dunjko
Dr
Adi Makmal
Mr
Hendrik Poulsen Nautrup
Prof.
Hans J. Briegel
(Institute for Theoretical Physics, University of Innsbruck)
