Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/82046
Title: | "Superstition" in the network : deep reinforcement learning plays deceptive games |
Authors: | Bontrager, Philip Khalifa, Ahmed Anderson, Damien Stephenson, Matthew Salge, Christoph Togelius, Julian |
Keywords: | Computer games Artificial intelligence Machine learning Reinforcement learning |
Issue Date: | 2019 |
Publisher: | Association for the Advancement of Artificial Intelligence (AAAI) |
Citation: | Bontrager, P., Khalifa, A., Anderson, D., Stephenson, M., Salge, C., & Togelius, J. (2019). "Superstition" in the network : deep reinforcement learning plays deceptive games. Proceedings of the Fifteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-19), Atlanta. 10-16. |
Abstract: | Deep reinforcement learning has learned to play many games well, but failed on others. To better characterize the modes and reasons of failure of deep reinforcement learners, we test the widely used Asynchronous Actor-Critic (A2C) algorithm on four deceptive games, which are specially designed to provide challenges to game-playing agents. These games are implemented in the General Video Game AI framework, which allows us to compare the behavior of reinforcement learningbased agents with planning agents based on tree search. We find that several of these games reliably deceive deep reinforcement learners, and that the resulting behavior highlights the shortcomings of the learning algorithm. The particular ways in which agents fail differ from how planning-based agents fail, further illuminating the character of these algorithms. We propose an initial typology of deceptions which could help us better understand pitfalls and failure modes of (deep) reinforcement learning. |
URI: | https://www.um.edu.mt/library/oar/handle/123456789/82046 |
ISSN: | 23340924 |
Appears in Collections: | Scholarly Works - InsDG |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Superstition_in_the_network_deep_reinforcement_learning_plays_deceptive_games_2019.pdf Restricted Access | 1.11 MB | Adobe PDF | View/Open Request a copy |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.