Modifying MCTS for Human-Like General Video Game Playing
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 2514-2519.
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.
@inproceedings{ijcai2016p358,
title = {Modifying MCTS for Human-Like General Video Game Playing},
author = {Khalifa, Ahmed and Isaksen, Aaron and Togelius, Julian and Nealen, Andy},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-16}},
publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
editor = {Subbarao Kambhampati},
pages = {2514--2519},
year = {2016},
month = {7},
url = {https://ijcai.org/proceedings/2016/358},
}
TY - CPAPER TI - Modifying MCTS for Human-Like General Video Game Playing AU - Khalifa, Ahmed AU - Isaksen, Aaron AU - Togelius, Julian AU - Nealen, Andy T2 - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16 PB - AAAI Press / International Joint Conferences on Artificial Intelligence PY - 2016 SP - 2514 EP - 2519 UR - https://ijcai.org/proceedings/2016/358 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
