id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
bracis-33605	Polar, Christian Delgado; Delgado, Karina Valdivia; Freire, Valdinei	Reinforcement Learning with Utility-Based Semantic for Goals	2024		.htm	text/html	7257	336	64	orcid.org/0000-0001-6123-64969,10, Karina Valdivia Delgado  ORCID: orcid.org/0000-0002-9120-89879 & Valdinei Freire  ORCID: orcid.org/0000-0003-0330-39319  Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 15413)) Included in the following conference series: Brazilian Conference on Intelligent Systems 378 Accesses Abstract Stochastic shortest path problems (SSPs) are Markov decision processes with goal states and the problem is to find policies to achieve the goal with the lowest possible expected cost. Download conference paper PDF Similar content being viewed by others $$\alpha $$ -MCMP: Trade-Offs Between Probability and Cost in SSPs with the MCMP Criterion Chapter © 2023 Trading Utility and Uncertainty: Applying the Value of Information to Resolve the Exploration–Exploitation Dilemma in Reinforcement Learning Chapter © 2021 A Linear Online Guided Policy Search Algorithm Chapter © 2017 1 Introduction Stochastic shortest path problems (SSPs) are Markov decision processes (MDPs) with a set of goal states.	cache/bracis-33605.htm	txt/bracis-33605.txt