no code implementations • 22 Jun 2023 • Adam Amos-Binks, Dustin Dannenhauer, Leilani H. Gilpin
StarCraft and Go are closed-world domains whose risks are known and mitigations well documented, ideal for learning through repetition.
no code implementations • 7 Jun 2023 • Mark Bercasio, Allison Wong, Dustin Dannenhauer
Developing artificial intelligence approaches to overcome novel, unexpected circumstances is a difficult, unsolved problem.
no code implementations • 7 May 2023 • Matthew Molineaux, Dustin Dannenhauer, Eric Kildebeck
We introduce a formal and theoretical framework for defining and categorizing environment transformations, changes to the world an agent inhabits.
no code implementations • 7 Mar 2022 • Dustin Dannenhauer, Matthew Molineaux, Michael W. Floyd, Noah Reifsnyder, David W. Aha
Complex, real-world domains may not be fully modeled for an agent, especially if the agent has never operated in the domain before.
no code implementations • 30 Jan 2022 • Michael Cox, Zahiduddin Mohammad, Sravya Kondrakunta, Ventaksamapth Raja Gogineni, Dustin Dannenhauer, Othalia Larue
Computational metacognition represents a cognitive systems perspective on high-order reasoning in integrated artificial systems that seeks to leverage ideas from human metacognition and from metareasoning approaches in artificial intelligence.
no code implementations • 28 Jun 2019 • Adam Amos-Binks, Dustin Dannenhauer
Anticipatory thinking is a complex cognitive process for assessing and managing risk in many contexts.
no code implementations • 5 Feb 2019 • Dustin Dannenhauer, Michael W. Floyd, Jonathan Decker, David W. Aha
In this paper we provide (1) a description of the state space of Dungeon Crawl Stone Soup, (2) a description of the components for our API, and (3) the potential benefits of evaluating AI agents in the Dungeon Crawl Stone Soup video game.