Flood-Fill Q-Learning Updates for Learning Redundant Policies in Order to Interact with a Computer Screen by Clicking

Autor:	Nathaniel du Preez-Wilkinson, Xuelei Hu, Marcus Gallagher
Rok vydání:	2018
Předmět:	Pixel Computer science business.industry Q-learning Flood fill Task (computing) Action (philosophy) Computer Science::Computer Vision and Pattern Recognition Reinforcement learning Computer vision Artificial intelligence State (computer science) business Equivalence (measure theory)
Zdroj:	AI 2018: Advances in Artificial Intelligence ISBN: 9783030039905 Australasian Conference on Artificial Intelligence
DOI:	10.1007/978-3-030-03991-2_49
Popis:	We present a specialisation of Q-learning for the problem of training an agent to click on a computer screen. In this problem formulation the agent sees the pixels of the screen as input, and selects a pixel as output. The task of selecting a pixel to click on involves selecting an action from a large discrete action space in which many of the actions are completely equivalent in terms of reinforcement learning state transitions. We propose to exploit this by performing simultaneous Q-learning updates for equivalent actions. We use the flood fill algorithm on the input image to determine the action (pixel) equivalence.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::eef2d573182d23e6ff61e0aaafa1a029 https://doi.org/10.1007/978-3-030-03991-2_49 Zobrazit plný text záznamu