Wait, But Why?: Assessing Behavior Explanation Strategies for Real-Time Strategy Games

Work in AI-based explanation systems has uncovered an interesting contradiction: people prefer and learn best from why explanations but expert esports commentators primarily answer what questions when explaining complex behavior in real-time strategy games. Three possible explanations for this contradiction are: 1.) broadcast audiences are well-informed and do not need why explanations; 2.) consuming why explanations in real-time is too cognitively demanding for audiences; or 3.) producing live why explanations is too difficult for commentators. We answer this open question by investigating the effects of explanation types and presentation modalities on audience recall and cognitive load in the context of an esports broadcast. We recruit 111 Dota 2 players and split them into three groups: the first group views a Dota 2 broadcast, the second group has the addition of an interactive map that provides what explanations, and the final group receives the interactive map with detailed why explanations. We find that participants who receive short interactive text prompts that provide what explanations outperform the no explanation group on a multiple-choice recall task. We also find that participants who receive detailed why explanations submit reports of cognitive load that are higher than the no explanation group. Our evidence supports the conclusion that informed audiences benefit from explanations but do not have the cognitive resources to process why answers in real-time. It also supports the conclusion that stacked explanation interventions across different modalities, like audio, interactivity, and text, can aid real-time comprehension when attention resources are limited. Together, our results indicate that interactive multimedia interfaces can be leveraged to quickly guide attention and provide low-cost explanations to improve intelligibility when time is too scarce for cognitively demanding why explanations.

[1]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[2]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[3]  Adam M. Smith,et al.  Crawling, indexing, and retrieving moments in videogames , 2018, FDG.

[4]  Amrita Sadarangani,et al.  Mental Models of Mere Mortals with Explanations of Reinforcement Learning , 2020, ACM Trans. Interact. Intell. Syst..

[5]  Yu-Gang Jiang,et al.  Deep Learning for Video Captioning: A Review , 2019, IJCAI.

[6]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[7]  Mark O. Riedl,et al.  Automated rationale generation: a technique for explainable AI and its effects on human perceptions , 2019, IUI.

[8]  Margaret M. Burnett,et al.  How the Experts Do It: Assessing and Explaining Agent Behaviors in Real-Time Strategy Games , 2017, CHI.

[9]  Morteza Behrooz,et al.  Story Quality as a Matter of Perception: Using Word Embeddings to Estimate Cognitive Interest , 2019, AIIDE.

[10]  George J. Spilich,et al.  Acquisition of domain-related information in relation to high and low domain knowledge. , 1979 .

[11]  Jakub W. Pachocki,et al.  Dota 2 with Large Scale Deep Reinforcement Learning , 2019, ArXiv.

[12]  Satoshi Matsuoka,et al.  Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn’t. , 2016, NAACL.

[13]  Jean Scholtz,et al.  How do visual explanations foster end users' appropriate trust in machine learning? , 2020, IUI.

[14]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[15]  Christopher D. Manning,et al.  Get To The Point: Summarization with Pointer-Generator Networks , 2017, ACL.

[16]  Enrico Costanza,et al.  Evaluating saliency map explanations for convolutional neural networks: a user study , 2020, IUI.

[17]  Carlos Guestrin,et al.  Model-Agnostic Interpretability of Machine Learning , 2016, ArXiv.

[18]  Jason Weston,et al.  A Neural Attention Model for Abstractive Sentence Summarization , 2015, EMNLP.

[19]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[20]  Fred G. W. C. Paas,et al.  The Efficiency of Instructional Conditions: An Approach to Combine Mental Effort and Performance Measures , 1992 .

[21]  Anind K. Dey,et al.  Assessing demand for intelligibility in context-aware applications , 2009, UbiComp.

[22]  Jonathan Hook,et al.  DAX: Data-Driven Audience Experiences in Esports , 2020, IMX.

[23]  Matthijs Douze,et al.  Fixing the train-test resolution discrepancy , 2019, NeurIPS.

[24]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[25]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[26]  Mark Chen,et al.  Language Models are Few-Shot Learners , 2020, NeurIPS.

[27]  Wojciech M. Czarnecki,et al.  Grandmaster level in StarCraft II using multi-agent reinforcement learning , 2019, Nature.

[28]  Maya R. Gupta,et al.  To Trust Or Not To Trust A Classifier , 2018, NeurIPS.

[29]  Anind K. Dey,et al.  Why and why not explanations improve the intelligibility of context-aware intelligent systems , 2009, CHI.

[30]  R. N. Davis,et al.  Web-based administration of a personality questionnaire: Comparison with traditional methods , 1999, Behavoir research methods, instruments & computers.

[31]  Trevor Darrell,et al.  Multimodal Explanations: Justifying Decisions and Pointing to the Evidence , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[32]  A. Acquisti,et al.  Beyond the Turk: Alternative Platforms for Crowdsourcing Behavioral Research , 2016 .

[33]  Jiajun Wu,et al.  Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling , 2016, NIPS.

[34]  M. Brysbaert How many words do we read per minute? A review and meta-analysis of reading rate , 2019 .

[35]  Rogelio E. Cardona-Rivera,et al.  Invisible Dynamic Mechanic Adjustment in Virtual Reality Games , 2020, 2020 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR).

[36]  Nancy Green,et al.  Bardic: Generating Multimedia Narratives for Game Logs , 2017, AIIDE Workshops.