IEEE - Institute of Electrical and Electronics Engineers, Inc. - Motivated Optimal Developmental Learning for Sequential Tasks Without Using Rigid Time-Discounts

Author(s): Dongshu Wang ; Yihai Duan ; Juyang Weng
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 October 2018
Volume: 29
Page(s): 4,917 - 4,931
ISSN (Electronic): 2162-2388
ISSN (Paper): 2162-237X
DOI: 10.1109/TNNLS.2017.2762720
Regular:

Many methods for reinforcement learning use symbolic representations-nonemergent-such as Q-learning. We use emergent representations here, without human handcrafted symbolic states (i.e.,... View More

Advertisement