Student of Games: A unified learning algorithm for both perfect and imperfect information games.

Games have a long history as benchmarks for progress in artificial intelligence. Approaches using search and learning produced strong performance across many perfect information games, and approaches using game-theoretic reasoning and learning demonstrated strong performance for specific imperfect information poker variants. We introduce Student of Games, a general-purpose algorithm that unifies previous approaches, combining guided search, self-play learning, and game-theoretic reasoning. Student of Games achieves strong empirical performance in large perfect and imperfect information games-an important step toward truly general algorithms for arbitrary environments. We prove that Student of Games is sound, converging to perfect play as available computation and approximation capacity increases. Student of Games reaches strong performance in chess and Go, beats the strongest openly available agent in heads-up no-limit Texas hold'em poker, and defeats the state-of-the-art agent in Scotland Yard, an imperfect information game that illustrates the value of guided search, learning, and game-theoretic reasoning.

DeepStack: Expert-level artificial intelligence in heads-up no-limit poker.

Artificial intelligence has seen several breakthroughs in recent years, with games often serving as milestones. A common feature of these games is that players have perfect information. Poker, the quintessential game of imperfect information, is a long-standing challenge problem in artificial intelligence. We introduce DeepStack, an algorithm for imperfect-information settings. It combines recursive reasoning to handle information asymmetry, decomposition to focus computation on the relevant decision, and a form of intuition that is automatically learned from self-play using deep learning. In a study involving 44,000 hands of poker, DeepStack defeated, with statistical significance, professional poker players in heads-up no-limit Texas hold'em. The approach is theoretically sound and is shown to produce strategies that are more difficult to exploit than prior approaches.

Space-Time Localization and Registration on the Beating Heart.

This paper presents a framework for localizing a miniature epicardial crawling robot, HeartLander, on the beating heart using only 6-degree-of-freedom position measurements from an electromagnetic position tracker and a dynamic surface model of the heart. Using only this information, motion and observation models of the system are developed such that a particle filter can accurately estimate not only the location of the robot on the surface of the heart, but also the pose of the heart in the world coordinate frame as well as the current physiological phase of the heart. The presented framework is then demonstrated in simulation on a dynamic 3-D model of the human heart and a robot motion model which accurately mimics the behavior of the HeartLander robot.

Towards localizing on the surface of the beating heart.

This paper presents preliminary work toward localizing on a surface which undergoes periodic deformation, as an aspect of research on HeartLander, a miniature epicardial crawling robot. Using only position measurements from the robot, the aim of this work is to use the nonuniform movements of the heart as features to aid in localization. Using a particle filter, with motion and observation models which accurately model the robotic system, registration and localization parameters can be quickly and accurately identified. The presented framework is demonstrated in simulation on dynamic 2-D models which approximate the deformation of the surface of the heart.

TGF beta-1 and neurological function after hypoxia-ischemia in adult rats.

The present study compared the short-term and long-term neuroprotective and neurobehavioral effects of transforming growth factor beta-1 (TGF beta-1) after hypoxic-ischemic injury in adult rats. TGF beta-1 (10 ng) or vehicle were administered intracerebroventricularly (i.c.v.) 2 h after hypoxia-ischemia. Adhesive removal test was assessed after 10 or 40 days, and the neuronal outcome then determined. TGF beta-1 significantly increased the area of intact cortex compared with vehicle 10 days after the injury, with a significant improvement in neurological function. In contrast, after 40 days recovery TGFbeta-1 neither improved neuronal outcome nor neurological function, suggesting TGFbeta-1 can transiently improve functional and histological recovery from hypoxia-ischemia.