Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/81986
Title: | Modifying MCTS for human-like general video game playing |
Authors: | Khalifa, Ahmed Isaksen, Aaron Togelius, Julian Nealen, Andy |
Keywords: | Computer games Artificial intelligence Machine learning |
Issue Date: | 2016 |
Publisher: | Association for the Advancement of Artificial Intelligence |
Citation: | Khalifa, A., Isaksen, A., Togelius, J., & Nealen, A. (2016). Modifying MCTS for human-like general video game playing. IJCAI'16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial, New York. 2514-2520. |
Abstract: | We address the problem of making general video game playing agents play in a human-like manner. To this end, we introduce several modifications of the UCT formula used in Monte Carlo Tree Search that biases action selection towards repeating the current action, making pauses, and limiting rapid switching between actions. Playtraces of human players are used to model their propensity for repeated actions; this model is used for biasing the UCT formula. Experiments show that our modified MCTS agent, called BoT, plays quantitatively similar to human players as measured by the distribution of repeated actions. A survey of human observers reveals that the agent exhibits human-like playing style in some games but not others. |
URI: | https://www.um.edu.mt/library/oar/handle/123456789/81986 |
Appears in Collections: | Scholarly Works - InsDG |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Modifying_MCTS_for_human-like_general_video_game_playing_2016.pdf | 209.86 kB | Adobe PDF | View/Open |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.