We propose a nonparametric additive model for estimating interpretable value functions in reinforcement learning. Learning effective adaptive clinical interventions that rely on digital phenotyping features is a major for concern medical practitioners. With respect to spine surgery, different post-operative recovery recommendations concerning patient mobilization can lead to significant variation in patient recovery. While reinforcement learning has achieved widespread success in domains such as games, recent methods heavily rely on black-box methods, such neural networks. Unfortunately, these methods hinder the ability of examining the contribution each feature makes in producing the final suggested decision. While such interpretations are easily provided in classical algorithms such as Least Squares Policy Iteration, basic linearity assumptions prevent learning higher-order flexible interactions between features. In this paper, we present a novel method that offers a flexible technique for estimating action-value functions without making explicit parametric assumptions regarding their additive functional form. This nonparametric estimation strategy relies on incorporating local kernel regression and basis expansion to obtain a sparse, additive representation of the action-value function. Under this approach, we are able to locally approximate the action-value function and retrieve the nonlinear, independent contribution of select features as well as joint feature pairs. We validate the proposed approach with a simulation study, and, in an application to spine disease, uncover recovery recommendations that are inline with related clinical knowledge.

Abstract--Currently there is no validated objective measure of pain. Recent neuroimaging studies have explored the feasibility of using functional near-infrared spectroscopy (fNIRS) to measure alterations in brain function in evoked and ongoing pain. In this study, we applied multi-task machine learning methods to derive a practical algorithm for pain detection derived from fNIRS signals in healthy volunteers exposed to a painful stimulus. Especially, we employed multi-task multiple kernel learning to account for the inter-subject variability in pain response. Our results support the use of fNIRS and machine learning techniques in developing objective pain detection, and also highlight the importance of adopting personalized analysis in the process.

While pain can be an unpleasant experience, it is a fundamental mechanism in organisms to help them identify threats. But should robots be programmed to experience pain? A new documentary from Cambridge University tackles this divisive issue, looking at the philosophical, ethical and social questions involved with artificially programming pain responses. Science fiction author Isaac Asimov first came up with the three'laws' of robotics in a story called'Runaround', published in 1942. The first of these laws says a robot may not injure a human being or, through inaction, allow a human being to come to harm.

Spot the Robot Dog gets kicked. Why was I programmed to feel pain?" The question is played for laughs, but like so many memorable scenes from this most beloved of shows, it also taps into some of the deeper, overarching themes that define our modern civilization. Pain is a fundamental fact of life for many organisms on our planet; a crucial mechanism for identifying what kinds of actions pose serious threats to our physical and mental health. As robots become more sophisticated and interactive, should they also be programmed to experience pain to prevent injuries to themselves or others, and if so, to what extent? "Pain in the Machine," a 12-minute documentary released by the University of Cambridge on Monday, tackles this multifaceted and controversial issue. The film offers insights from artificial intelligence thought leaders, practicing physicians, and other interdisciplinary experts, and contrasts them with iconic popular culture moments that point to the larger philosophical questions inherent to artificially programming pain responses--including a nod to burning robot bit in The Simpsons. Like so many AI research fields, evaluating the utility and benefits of pain in robots inevitably flips the mirror back on our understanding of how those experiences function and protect us in our own lives. "Pain has fascinated philosophers for centuries," Ben Seymour, a Cambridge-based expert on the computational and systems neuroscience of pain, comments in the documentary. "Indeed, some people consider pain to be the pinnacle of consciousness.

Why was I programmed to feel pain?" The question is played for laughs, but like so many memorable scenes from this most beloved of shows, it also taps into some of the deeper, overarching themes that define our modern civilization. Pain is a fundamental fact of life for many organisms on our planet; a crucial mechanism for identifying what kinds of actions pose serious threats to our physical and mental health. As robots become more sophisticated and interactive, should they also be programmed to experience pain to prevent injuries to themselves or others, and if so, to what extent? "Pain in the Machine," a 12-minute documentary released by the University of Cambridge on Monday, tackles this multifaceted and controversial issue. The film offers insights from artificial intelligence thought leaders, practicing physicians, and other interdisciplinary experts, and contrasts them with iconic popular culture moments that point to the larger philosophical questions inherent to artificially programming pain responses--including a nod to burning robot bit in The Simpsons. Like so many AI research fields, evaluating the utility and benefits of pain in robots inevitably flips the mirror back on our understanding of how those experiences function and protect us in our own lives. "Pain has fascinated philosophers for centuries," Ben Seymour, a Cambridge-based expert on the computational and systems neuroscience of pain, comments in the documentary. "Indeed, some people consider pain to be the pinnacle of consciousness.

Robots are one step closer to being able to experience an essential human feeling: pain. Researchers in Germany are creating a "nervous system" that would mimic a pain response in robots, allowing them to quickly react and avoid harmful situations. "Pain is a system that protects us," researcher Johannes Kuehn told a conference of engineers last week. "When we evade from the source of pain, it helps us not get hurt." The researchers programmed their robot to experience a "hierarchy" of pain through a variety of stimuli, such as blunt force or heat. Depending on the threat, such as a harsh movement or intense heat, the robot is programmed to retract to the danger.

Robots are one step closer to being able to experience an essential human feeling: pain. Researchers in Germany are currently creating a "nervous system" that would mimic a pain response in robots, allowing them to quickly react and avoid harmful situations. "Pain is a system that protects us," researcher Johannes Kuehn told a conference of engineers last week. "When we evade from the source of pain, it helps us not get hurt." The researchers programmed their robot to experience a "hierarchy" of pain through a variety of different stimuli, such as blunt force or heat.