Explanation-Based Reward Coaching to Improve Human Performance via Reinforcement Learning

Tabrez, Aaquib; Agrawal, Shivendra; Hayes, Bradley

doi:10.1109/hri.2019.8673104

Cited by 52 publications

(48 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The agent could steer evacuees away from a possible hazardous state either by blocking their path or by verbally updating their internal model ("fire in next hallway") to encourage alternative, less dangerous paths. Various challenges related to behavior manipulation include accurately modeling human behavior [30], leveraging human models to find failure modes [94], and succinctly generating persuasive human intelligible semantic updates (or executing mitigating actions) [68]. This concept of behavior modeling has additionally been extended to intelligent teaching or coaching for effective personalized learning [95].…”

Section: Emerging Fields and Discussionmentioning

confidence: 99%

“…Explainability Explainability deals with the understanding of the mechanisms by which a robot operates and the ability to explain robots' behavior or underlying logic [30,68]. Existing works in explainable AI assess the effects of explainability through self-reported understanding of the agent behavior, successful task completions, system faults, task completion time, number of irreparable mistakes, and trust in automation.…”

Section: Evaluation Methodsmentioning

confidence: 99%

“…Another recent approach for human behavior modeling is the Reward Augmentation and Repair through Explanation (RARE) framework for estimating and improving a collaborators' task understanding. Here, Tabrez et al provided a computational framework for human reward function estimation via a set of possible Hidden Markov Models (HMMs) [30], representing a task's reward function and partially deficient variants (e.g., missing reward information). The collaborative agent must infer the most likely HMM for explaining the teammates' behavior, which in turn indicates a plausible underlying reward function for explaining the human's actions.…”

Section: First-order Mental Modelsmentioning

confidence: 99%

See 2 more Smart Citations

A Survey of Mental Modeling Techniques in Human–Robot Teaming

2020

Self Cite

View full text Add to dashboard Cite

Purpose of Review As robots become increasingly prevalent and capable, the complexity of roles and responsibilities assigned to them as well as our expectations for them will increase in kind. For these autonomous systems to operate safely and efficiently in human-populated environments, they will need to cooperate and coordinate with human teammates. Mental models provide a formal mechanism for achieving fluent and effective teamwork during human-robot interaction by enabling awareness between teammates and allowing for coordinated action. Recent Findings Much recent research in human-robot interaction has made use of standardized and formalized mental modeling techniques to great effect, allowing for a wider breadth of scenarios in which a robotic agent can act as an effective and trustworthy teammate. Summary This paper provides a structured overview of mental model theory and methodology as applied to human-robot teaming. Also discussed are evaluation methods and metrics for various aspects of mental modeling during human-robot interaction, as well as recent emerging applications and open challenges in the field. Keywords Human-robot teaming • Mental models • Human-robot interaction • Theory of mind This article belongs to the Topical Collection on Service and Interactive Robotics

show abstract

Section: Emerging Fields and Discussionmentioning

confidence: 99%

Section: Evaluation Methodsmentioning

confidence: 99%

Section: First-order Mental Modelsmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Mental Modeling Techniques in Human–Robot Teaming

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…A major limitation of the studies presented in this review is that many approaches were either not tested with users (17 papers), or when they did, limited details of the testing were published, failing to describe where the participants were recruited from, how many were recruited, or if the participants were knowledgeable in Machine Learning (Pynadath et al, 2018 ; Tabrez and Hayes, 2019 ; Tabrez et al, 2019 ). Participant counts varied greatly, with one paper using 3 experts (Wang et al, 2018 ), others with students (Iyer et al, 2018 ), n = 40; and Greydanus et al ( 2018 ), n = 31, and three recruiting using Amazon Mechanical Turk 3 (Huang et al, 2019 , n = 191; Madumal et al, 2020 , n = 120; and Ehsan et al, 2019 , n = 65 and n = 60).…”

Section: Discussionmentioning

confidence: 99%

Explainable AI and Reinforcement Learning—A Systematic Review of Current Approaches and Trends

Wells

Bednarz

2021

Front. Artif. Intell.

119

View full text Add to dashboard Cite

Research into Explainable Artificial Intelligence (XAI) has been increasing in recent years as a response to the need for increased transparency and trust in AI. This is particularly important as AI is used in sensitive domains with societal, ethical, and safety implications. Work in XAI has primarily focused on Machine Learning (ML) for classification, decision, or action, with detailed systematic reviews already undertaken. This review looks to explore current approaches and limitations for XAI in the area of Reinforcement Learning (RL). From 520 search results, 25 studies (including 5 snowball sampled) are reviewed, highlighting visualization, query-based explanations, policy summarization, human-in-the-loop collaboration, and verification as trends in this area. Limitations in the studies are presented, particularly a lack of user studies, and the prevalence of toy-examples and difficulties providing understandable explanations. Areas for future study are identified, including immersive visualization, and symbolic representation.

show abstract

“…Here the human does not know the reward function but can learn it through several interactions, whereas the robot only observes the human interactions and not the reward associated with it. Tabrez et al used their Reward Augmentation and Repair through Explanation (RARE) framework for estimating task understanding where the autonomous agent detects potential causes of system failures and uses human-interpretable feedback for model correction [48]. Nikolaidas et al [29] described a humanrobot cross-training framework using reinforcement learning techniques where humans and robots switch roles to improve the overall performance.…”

Section: Reinforcement Learning Techniques To Identify Better Reward mentioning

confidence: 99%

Mutual Reinforcement Learning with Robot Trainers

Roy

Kieson

Abramson

et al. 2019

2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI)

View full text Add to dashboard Cite

Recently, collaborative robots have begun to train humans to achieve complex tasks, and the mutual information exchange between them can lead to successful robot-human collaborations. In this paper we demonstrate the application and effectiveness of a new approach called mutual reinforcement learning (MRL), where both humans and autonomous agents act as reinforcement learners in a skill transfer scenario over continuous communication and feedback. An autonomous agent initially acts as an instructor who can teach a novice human participant complex skills using the MRL strategy. While teaching skills in a physical (block-building) (n = 34) or simulated (Tetris) environment (n = 31), the expert tries to identify appropriate reward channels preferred by each individual and adapts itself accordingly using an exploration-exploitation strategy. These reward channel preferences can identify important behaviors of the human participants, because they may well exercise the same behaviors in similar situations later. In this way, skill transfer takes place between an expert system and a novice human operator. We divided the subject population into three groups and observed the skill transfer phenomenon, analyzing it with Simpson"s psychometric model. 5-point Likert scales were also used to identify the cognitive models of the human participants. We obtained a shared cognitive model which not only improves human cognition but enhances the robot's cognitive strategy to understand the mental model of its human partners while building a successful robot-human collaborative framework.

show abstract

Explanation-Based Reward Coaching to Improve Human Performance via Reinforcement Learning

Cited by 52 publications

References 18 publications

A Survey of Mental Modeling Techniques in Human–Robot Teaming

A Survey of Mental Modeling Techniques in Human–Robot Teaming

Explainable AI and Reinforcement Learning—A Systematic Review of Current Approaches and Trends

Mutual Reinforcement Learning with Robot Trainers

Contact Info

Product

Resources

About