ترغب بنشر مسار تعليمي؟ اضغط هنا

Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabi

79   0   0.0 ( 0 )
 نشر من قبل Ho Chit Siu
 تاريخ النشر 2021
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Deep reinforcement learning has generated superhuman AI in competitive games such as Go and StarCraft. Can similar learning techniques create a superior AI teammate for human-machine collaborative games? Will humans prefer AI teammates that improve objective team performance or those that improve subjective metrics of trust? In this study, we perform a single-blind evaluation of teams of humans and AI agents in the cooperative card game Hanabi, with both rule-based and learning-based agents. In addition to the game score, used as an objective metric of the human-AI team performance, we also quantify subjective measures of the humans perceived performance, teamwork, interpretability, trust, and overall preference of AI teammate. We find that humans have a clear preference toward a rule-based AI teammate (SmartBot) over a state-of-the-art learning-based AI teammate (Other-Play) across nearly all subjective metrics, and generally view the learning-based agent negatively, despite no statistical difference in the game score. This result has implications for future AI design and reinforcement learning benchmarking, highlighting the need to incorporate subjective metrics of human-AI teaming rather than a singular focus on objective task performance.



قيم البحث

اقرأ أيضاً

We introduce EvalAI, an open source platform for evaluating and comparing machine learning (ML) and artificial intelligence algorithms (AI) at scale. EvalAI is built to provide a scalable solution to the research community to fulfill the critical nee d of evaluating machine learning models and agents acting in an environment against annotations or with a human-in-the-loop. This will help researchers, students, and data scientists to create, collaborate, and participate in AI challenges organized around the globe. By simplifying and standardizing the process of benchmarking these models, EvalAI seeks to lower the barrier to entry for participating in the global scientific effort to push the frontiers of machine learning and artificial intelligence, thereby increasing the rate of measurable progress in this domain.
The paper describes a Multisource AI Scorecard Table (MAST) that provides the developer and user of an artificial intelligence (AI)/machine learning (ML) system with a standard checklist focused on the principles of good analysis adopted by the intel ligence community (IC) to help promote the development of more understandable systems and engender trust in AI outputs. Such a scorecard enables a transparent, consistent, and meaningful understanding of AI tools applied for commercial and government use. A standard is built on compliance and agreement through policy, which requires buy-in from the stakeholders. While consistency for testing might only exist across a standard data set, the community requires discussion on verification and validation approaches which can lead to interpretability, explainability, and proper use. The paper explores how the analytic tradecraft standards outlined in Intelligence Community Directive (ICD) 203 can provide a framework for assessing the performance of an AI system supporting various operational needs. These include sourcing, uncertainty, consistency, accuracy, and visualization. Three use cases are presented as notional examples that support security for comparative analysis.
Reinforcement learning (RL) agents in human-computer interactions applications require repeated user interactions before they can perform well. To address this cold start problem, we propose a novel approach of using cognitive models to pre-train RL agents before they are applied to real users. After briefly reviewing relevant cognitive models, we present our general methodological approach, followed by two case studies from our previous and ongoing projects. We hope this position paper stimulates conversations between RL, HCI, and cognitive science researchers in order to explore the full potential of the approach.
Conversational agents (CAs) represent an emerging research field in health information systems, where there are great potentials in empowering patients with timely information and natural language interfaces. Nevertheless, there have been limited att empts in establishing prescriptive knowledge on designing CAs in the healthcare domain in general, and diabetes care specifically. In this paper, we conducted a Design Science Research project and proposed three design principles for designing health-related CAs that embark on artificial intelligence (AI) to address the limitations of existing solutions. Further, we instantiated the proposed design and developed AMANDA - an AI-based multilingual CA in diabetes care with state-of-the-art technologies for natural-sounding localised accent. We employed mean opinion scores and system usability scale to evaluate AMANDAs speech quality and usability, respectively. This paper provides practitioners with a blueprint for designing CAs in diabetes care with concrete design guidelines that can be extended into other healthcare domains.
Machine learning is challenging the way we make music. Although research in deep generative models has dramatically improved the capability and fluency of music models, recent work has shown that it can be challenging for humans to partner with this new class of algorithms. In this paper, we present findings on what 13 musician/developer teams, a total of 61 users, needed when co-creating a song with AI, the challenges they faced, and how they leveraged and repurposed existing characteristics of AI to overcome some of these challenges. Many teams adopted modular approaches, such as independently running multiple smaller models that align with the musical building blocks of a song, before re-combining their results. As ML models are not easily steerable, teams also generated massive numbers of samples and curated them post-hoc, or used a range of strategies to direct the generation, or algorithmically ranked the samples. Ultimately, teams not only had to manage the flare and focus aspects of the creative process, but also juggle them with a parallel process of exploring and curating multiple ML models and outputs. These findings reflect a need to design machine learning-powered music interfaces that are more decomposable, steerable, interpretable, and adaptive, which in return will enable artists to more effectively explore how AI can extend their personal expression.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا