2026-05-25T01:21:23Zhttps://keep.lib.asu.edu/oai/request

oai:keep.lib.asu.edu:node-1309122024-12-18T20:58:30Zoai_pmh:alloai_pmh:repo_items

130912 https://hdl.handle.net/2286/R.I.62598 http://rightsstatements.org/vocab/InC/1.0/ 2020-12 24 pages eng Ciudad, Erick Marcel Meuth, Ryan Kobayashi, Yoshihiro Computing and Informatics Program Computer Science and Engineering Program Barrett, The Honors College Text Video games often feature agents that the human player interacts with to overcome.<br/>Designing these agents to cover every case of human interaction is difficult, and usually<br/>imperfect, as human players are capable of learning to overcome these agents in unintended<br/>ways. Artificial intelligence is a growing field that seeks to solve problems by simulating<br/>learning in specific environments. The aim of this paper is to explore the applications that the<br/>self play learning branch of artificial intelligence may pose on game development in the future,<br/>and to attempt to implement a working version of a self play agent learning to play a Pokemon<br/>battle. Originally designed Pokemon battle behavior is often suboptimal, getting stuck making<br/>ineffective or incorrect choices, so training a self play model to learn the strategy and structure of<br/>Pokemon battles from a clean slate would result in an organic agent that would outperform the<br/>original behavior of the computer controlled agents. Though unsuccessful in my implementation,<br/>this paper serves as a record of the exploration of this field, and a log of what worked and what<br/>did not, in order to benefit any future person interested in the same topics. Self Play Machine learning Videogames Game Design Self Play Machine Learning and Pokemon