Anticipatory Classifier System with Average Reward Criterion in Discretized Multi-Step Environments
Sign Up to like & getrecommendations! Published in 2021 at "Applied Sciences"
DOI: 10.3390/app11031098
Abstract: Initially, Anticipatory Classifier Systems (ACS) were designed to address both single and multistep decision problems. In the latter case, the objective was to maximize the total discounted rewards, usually based on Q-learning algorithms. Studies on… read more here.
Keywords: system; system average; anticipatory classifier; reward criterion ... See more keywords