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:
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