Fast Adaptation with Meta-Reinforcement Learning for Trust Modelling in Human-Robot Interaction

Gao, Yuan; Sibirtseva, Elena; Castellano, Ginevra; Kragić, Danica

doi:10.1109/iros40897.2019.8967924

Cited by 14 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, it can be using different reinforcement learning algorithms to select the behaviours such as Exp3 v.s. policy gradient based solution for Exp3 problem, together with meta-learning (see Gao et al (2019)). Secondly, we can improve the method to compute the emotional state of the users by using a state of the art emotion recognition API and also rethinking the method to compute emotion on the given state in the game.…”

Section: Discussionmentioning

confidence: 99%

Emotion and memory model for social robots: a reinforcement learning based behaviour selection

Ahmad

Gao

Alnajjar

et al. 2021

Behaviour & Information Technology

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a reinforcement learning (RL) mechanism for social robots to select an action based on users' learning performance and social engagement. We applied this behavior selection mechanism to extend the emotion and memory model, which allows a robot to create a memory account of the user's emotional events and adapt its behavior based on the developed memory. We evaluated the model in a vocabulary-learning task at a school during a children's game involving robot interaction to see if the model results in maintaining engagement and improving vocabulary learning across the four different interaction sessions. Generally, we observed positive findings based on child vocabulary learning and sustaining social engagement during all sessions. Compared to the trends of a previous study, we observed a higher level of social engagement across sessions in terms of the duration of the user gaze toward the robot. For vocabulary retention, we saw similar trends in general but also showing high vocabulary retention across some sessions. The findings indicate the benefits of applying RL techniques that have a reward system based on multi-modal user signals or cues.

show abstract

Section: Discussionmentioning

confidence: 99%

Emotion and memory model for social robots: a reinforcement learning based behaviour selection

Ahmad

Gao

Alnajjar

et al. 2021

Behaviour & Information Technology

Self Cite

View full text Add to dashboard Cite

show abstract

“…In particular, such extrinsic perspectives broadly include the explainability, privacy protection for sensitive individual information, ethics, and general human trust on trained RL agents or models. Different trustworthy RL algorithms have also been studied in the literature by considering such human-centric design [4,51,128,175] to bridge the trust with human.…”

Section: How To Achieve the Human-centric Design For Trustworthy Rl?mentioning

confidence: 99%

Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability

Xu¹,

Liu²,

Huang³

et al. 2022

Preprint

View full text Add to dashboard Cite

A trustworthy reinforcement learning algorithm should be competent in solving challenging real-world problems, including robustly handling uncertainties, satisfying safety constraints to avoid catastrophic failures, and generalizing to unseen scenarios during deployments. This study aims to overview these main perspectives of trustworthy reinforcement learning considering its intrinsic vulnerabilities on robustness, safety, and generalizability. In particular, we give rigorous formulations, categorize corresponding methodologies, and discuss benchmarks for each perspective. Moreover, we provide an outlook section to spur promising future directions with a brief discussion on extrinsic vulnerabilities considering human feedback. We hope this survey could bring together separate threads of studies together in a unified framework and promote the trustworthiness of reinforcement learning. CCS Concepts: • Computing methodologies → Reinforcement learning; Markov decision processes; • Security and privacy → Social aspects of security and privacy; • Computer systems organization → Robotics; • Hardware → Safety critical systems.

show abstract

“…Robots can use speech to change the content of the conversation (Gamborino and Fu, 2018) or to answer a question about the surrounding environment (Bui and Chong, 2018). Robots can use dialogue to gather information during collaborative teleoperation (Fong et al, 2003), to engender trust in an escape room (Gao et al, 2019), or to facilitate collaboration between two targets of assistance (Strohkorb et al, 2016). Robots can also talk about themselves to influence a user's view of themselves.…”

Section: Human Brainmentioning

confidence: 99%

Helping People Through Space and Time: Assistance as a Perspective on Human-Robot Interaction

2022

View full text Add to dashboard Cite

As assistive robotics has expanded to many task domains, comparing assistive strategies among the varieties of research becomes increasingly difficult. To begin to unify the disparate domains into a more general theory of assistance, we present a definition of assistance, a survey of existing work, and three key design axes that occur in many domains and benefit from the examination of assistance as a whole. We first define an assistance perspective that focuses on understanding a robot that is in control of its actions but subordinate to a user’s goals. Next, we use this perspective to explore design axes that arise from the problem of assistance more generally and explore how these axes have comparable trade-offs across many domains. We investigate how the assistive robot handles other people in the interaction, how the robot design can operate in a variety of action spaces to enact similar goals, and how assistive robots can vary the timing of their actions relative to the user’s behavior. While these axes are by no means comprehensive, we propose them as useful tools for unifying assistance research across domains and as examples of how taking a broader perspective on assistance enables more cross-domain theorizing about assistance.

show abstract

Fast Adaptation with Meta-Reinforcement Learning for Trust Modelling in Human-Robot Interaction

Cited by 14 publications

References 37 publications

Emotion and memory model for social robots: a reinforcement learning based behaviour selection

Emotion and memory model for social robots: a reinforcement learning based behaviour selection

Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability

Helping People Through Space and Time: Assistance as a Perspective on Human-Robot Interaction

Contact Info

Product

Resources

About