Title :
Autonomous reinforcement of behavioral sequences in neural dynamics
Author :
Kazerounian, Sohrob ; Luciw, Matthew ; Richter, Maximilian ; Sandamirskaya, Yulia
Author_Institution :
Ist. Dalle Molle di Studi sull´Intell. Artificiale (IDSIA), Lugano, Switzerland
Abstract :
We introduce a dynamic neural algorithm called Dynamic Neural (DN) SARSA(λ) for learning a behavioral sequence from delayed reward. DN-SARSA(λ) combines Dynamic Field Theory models of behavioral sequence representation, classical reinforcement learning, and a computational neuroscience model of working memory, called Item and Order working memory, which serves as an eligibility trace. DN-SARSA(λ) is implemented on both a simulated and real robot that must learn a specific rewarding sequence of elementary behaviors from exploration. Results show DN-SARSA(λ) performs on the level of the discrete SARSA(λ), validating the feasibility of general reinforcement learning without compromising neural dynamics.
Keywords :
behavioural sciences; learning (artificial intelligence); DN; autonomous reinforcement; behavioral sequence representation; classical reinforcement learning; computational neuroscience model; delayed reward; dynamic field theory models; dynamic neural algorithm; item working memory; neural dynamics; order working memory; Computational modeling; Computer architecture; Discrete Fourier transforms; Integrated circuit modeling; Learning (artificial intelligence); Robot sensing systems; Standards;
Conference_Titel :
Neural Networks (IJCNN), The 2013 International Joint Conference on
Conference_Location :
Dallas, TX
Print_ISBN :
978-1-4673-6128-6
DOI :
10.1109/IJCNN.2013.6706877
