Intra-task Curriculum Learning for Faster Reinforcement Learning in Video Games

Autor:	Marcus Gallagher, Nathaniel du Preez-Wilkinson, Xuelei Hu
Rok vydání:	2018
Předmět:	business.industry Computer science Order (business) Control (management) Reinforcement learning Artificial intelligence business Curriculum State of the Environment Task (project management)
Zdroj:	AI 2018: Advances in Artificial Intelligence ISBN: 9783030039905 Australasian Conference on Artificial Intelligence
DOI:	10.1007/978-3-030-03991-2_6
Popis:	In this paper we present a new method for improving reinforcement learning training times under the following two assumptions: (1) we know the conditions under which the environment gives reward; and (2) we can control the initial state of the environment at the beginning of a training episode. Our method, called intra-task curriculum learning, presents the different episode starting states to an agent in order of increasing distance to immediate reward.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::53002caee08a4698609666cde5044e5f https://doi.org/10.1007/978-3-030-03991-2_6 Zobrazit plný text záznamu