Mental models of mere mortals with explanations of reinforcement learning

A Anderson, J Dodge, A Sadarangani… - ACM Transactions on …, 2020 - dl.acm.org
How should reinforcement learning (RL) agents explain themselves to humans not trained in
AI? To gain insights into this question, we conducted a 124-participant, four-treatment …

After-action review for AI (AAR/AI)

J Dodge, R Khanna, J Irvine, KH Lam, T Mai… - ACM Transactions on …, 2021 - dl.acm.org
Explainable AI is growing in importance as AI pervades modern society, but few have
studied how explainable AI can directly support people trying to assess an AI agent. Without …

Finding AI's faults with AAR/AI: An empirical study

R Khanna, J Dodge, A Anderson, R Dikkala… - ACM Transactions on …, 2022 - dl.acm.org
Would you allow an AI agent to make decisions on your behalf? If the answer is “not always,”
the next question becomes “in what circumstances”? Answering this question requires …

Toward foraging for understanding of StarCraft agents: An empirical study

S Penney, J Dodge, C Hilderbrand… - Proceedings of the 23rd …, 2018 - dl.acm.org
Assessing and understanding intelligent agents is a difficult task for users that lack an AI
background. A relatively new area, called" Explainable AI," is emerging to help address this …

How the experts do it: Assessing and explaining agent behaviors in real-time strategy games

J Dodge, S Penney, C Hilderbrand… - Proceedings of the …, 2018 - dl.acm.org
How should an AI-based explanation system explain an agent's complex behavior to
ordinary end users who have no background in AI? Answering this question is an active …

Keeping it" organized and logical" after-action review for AI (AAR/AI)

T Mai, R Khanna, J Dodge, J Irvine, KH Lam… - Proceedings of the 25th …, 2020 - dl.acm.org
Explainable AI (XAI) is growing in importance as AI pervades modern society, but few have
studied how XAI can directly support people trying to assess an AI agent. Without a rigorous …

Determinants of victory in Esports-StarCraft II

A Białecki, J Gajewski, P Białecki, A Phatak… - Multimedia Tools and …, 2023 - Springer
Esports offer a unique opportunity to conduct human performance studies, as they use
modern hardware and software as an operation platform. Insights on gameplay and …

Parallel system based quantitative assessment and self-evolution (PLASE) for artificial intelligence of the active power corrective control

TY Zhang, J Zhang, FY Wang, PD Xu… - CSEE Journal of …, 2023 - ieeexplore.ieee.org
In artificial intelligence (AI) based-complex power system management and control
technology, one of the urgent tasks is to evaluate AI intelligence and invent a way of …

Conceptualizing online groups as multidimensional networks

B Yan, YJ Kim, AB Hollingshead, DP Brandon - 2018 - academic.oup.com
The advancements in information and communication technologies in the past few decades,
as represented by ubiquitous computing, social media, and artificial intelligence, have made …

The shoutcasters, the game enthusiasts, and the AI: Foraging for explanations of real-time strategy players

S Penney, J Dodge, A Anderson… - ACM Transactions on …, 2021 - dl.acm.org
Assessing and understanding intelligent agents is a difficult task for users who lack an AI
background.“Explainable AI”(XAI) aims to address this problem, but what should be in an …