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

Autor: Marcus Gallagher, Nathaniel du Preez-Wilkinson, Xuelei Hu
Rok vydání: 2018
Předmět:
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