Planning and visualization for a smart meeting room assistant1

Chakraborti, Tathagata; Fadnis, Kshitij P.; Talamadupula, Kartik; Dholakia, Mishal; Srivastava, Biplav; Kephart, Jeffrey O.; Bellamy, Rachel K. E.

doi:10.3233/aic-180609

Cited by 9 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Krarup et al [130] uses waypoints for explanation, where this use of an execution-trace is a similar approach to that of rule traces and tracing nodes through a BN or DN. Similar approaches of generating explanations from actions using a model can be seen in other recent research [60,69,122,123,46,107,39,87,40,29,237,198,103]. Fox et al [78] identifies several questions that XAIP can answer.…”

Section: Model-based Xrl-behaviourmentioning

confidence: 67%

Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey

Dazeley¹,

Vamplew²,

Cruz³

2021

Preprint

View full text Add to dashboard Cite

Broad Explainable Artificial Intelligence (Broad-XAI) moves away from interpreting individual decisions based on a single datum and aims to provide integrated explanations from multiple machine learning algorithms into a coherent explanation of an agent's behaviour that is aligned to the communication needs of the explainee. Reinforcement Learning (RL) methods, we propose, provide a potential backbone for the cognitive model required for the development of Broad-XAI. RL represents a suite of approaches that have had increasing success in solving a range of sequential decision-making problems. However, these algorithms all operate as black-box problem solvers, where they obfuscate their decision-making policy through a complex array of values and functions. EXplainable RL (XRL) is relatively recent field of research that aims to develop techniques to extract concepts from the agent's: perception of the environment; intrinsic/extrinsic motivations/beliefs; Q-values, goals and objectives. This paper aims to introduce a conceptual framework, called the Causal XRL Framework (CXF), that unifies the current XRL research and uses RL as a backbone to the development of Broad-XAI. Additionally, we recognise that RL methods have the ability to incorporate a range of technologies to allow agents to adapt to their environment. CXF is designed for the incorporation of many standard RL extensions and integrated with external ontologies and communication facilities so that the agent can answer questions that explain outcomes and justify its decisions. This paper aims to: establish XRL as a distinct branch of Explainable Artificial Intelligence (XAI); introduce a conceptual framework for XRL; review existing approaches explaining agent behaviour; and identify opportunities for future research. Finally, this paper will discuss how additional information can be extracted and ultimately integrated into models of communication, facilitating the development of Broad-XAI.

show abstract

Section: Model-based Xrl-behaviourmentioning

confidence: 67%

Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey

Dazeley¹,

Vamplew²,

Cruz³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…We adapt the popular idea of using the causal chain from an action to the goal as the justification for its role in the plan (c.f. (Veloso 1992;Seegebarth et al 2012;Bercher et al 2014;Chakraborti et al 2019;Kambhampati 1990)) to individual facts. We identify whether an action contributed something to the goal by performing a regression from the goal over each action that was executed by the agent.…”

Section: "Why?" Questionsmentioning

confidence: 99%

Explainable Composition of Aggregated Assistants

Sreedharan¹,

Chakraborti²,

Rizk³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

A new design of an AI assistant that has become increasingly popular is that of an "aggregated assistant" -realized as an orchestrated composition of several individual skills or agents that can each perform atomic tasks. In this paper, we will talk about the role of planning in the automated composition of such assistants and explore how concepts in automated planning can help to establish transparency of the inner workings of the assistant to the end-user.

show abstract

“…IBM has developed a business group decision-making system. 149 The moral machine 150 elicits preferences about ethical issues and can be used to help people make ethical decisions, 151 for example, by voting. 131 Societal tradeoffs between activities can be decided by aggregating agents' individual tradeoffs.…”

Section: Ai-empowered Group Decision Makingmentioning

confidence: 99%

Group decision making under uncertain preferences: powered by AI, empowered by AI

Xia

2022

Annals of the New York Academy of Sciences

View full text Add to dashboard Cite

Group decision making is an important, long-standing, and ubiquitous problem in all societies, where collective decisions must be made by a group of agents despite individual conflicting preferences. This has been a classical and active topic for research in many disciplines, including economics, political science, cognitive and behavioral sciences, statistics, mathematics, and computer science. In this article, I survey some recent progress in theoretical, algorithmic, and engineering work toward building AI-powered intelligent systems to help agents make group decisions based on uncertain preferences; these systems leverage principles, ideas, and methodologies from multiple disciplines. Empowered by AI, group decision making can handle a broader range of situations at relatively large scales.

show abstract

Planning and visualization for a smart meeting room assistant1

Cited by 9 publications

References 19 publications

Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey

Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey

Explainable Composition of Aggregated Assistants

Group decision making under uncertain preferences: powered by AI, empowered by AI

Contact Info

Product

Resources

About