2018 ESC/EACTS Guidelines on myocardial revascularization.

Much has been written about theory and practice in the law, and the tension between practitioners and theorists. Judges do not cite theoretical articles often; they rarely "apply" theories to particular cases. These arguments are not revisited. Instead the Essay explores the working and interaction of theory and practice, practitioners and theorists. The Essay starts with a story about solving a legal issue using our intellectual tools - theory, practice, and their progenies: experience and "gut." Next the Essay elaborates on the nature of theory, practice, experience and "gut." The third part of the Essay discusses theories that are helpful to practitioners and those that are less helpful. The Essay concludes that practitioners theorize, and theorists practice. They use these intellectual tools differently because the goals and orientations of theorists and practitioners, and the constraints under which they act, differ. Theory, practice, experience and "gut" help us think, remember, decide and create. They complement each other like the two sides of the same coin: distinct but inseparable.

Of Theory and Practice

Highway Capacity Manual改訂の動向--テイラ-教授の講演より

Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering. It can be combined with an arbitrary off-policy RL algorithm and may be seen as a form of implicit curriculum. We demonstrate our approach on the task of manipulating objects with a robotic arm. In particular, we run experiments on three different tasks: pushing, sliding, and pick-and-place, in each case using only binary rewards indicating whether or not the task is completed. Our ablation studies show that Hindsight Experience Replay is a crucial ingredient which makes training possible in these challenging environments. We show that our policies trained on a physics simulation can be deployed on a physical robot and successfully complete the task. The video presenting our experiments is available at https://goo.gl/SMrQnI.

/pdf/hindsight-experience-replay-5c7658gepb.pdf

Hindsight Experience Replay

Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained via imitation learning cannot be controlled at test time. A vehicle trained end-to-end to imitate an expert cannot be guided to take a specific turn at an upcoming intersection. This limits the utility of such systems. We propose to condition imitation learning on high-level command input. At test time, the learned driving policy functions as a chauffeur that handles sensorimotor coordination but continues to respond to navigational commands. We evaluate different architectures for conditional imitation learning in vision-based driving. We conduct experiments in realistic three-dimensional simulations of urban driving and on a 1/5 scale robotic truck that is trained to drive in a residential area. Both systems drive based on visual input yet remain responsive to high-level navigational commands.

End-to-End Driving Via Conditional Imitation Learning

We introduce a method for constructing skills capable of solving tasks drawn from a distribution of parameterized reinforcement learning problems. The method draws example tasks from a distribution of interest and uses the corresponding learned policies to estimate the topology of the lower-dimensional piecewise-smooth manifold on which the skill policies lie. This manifold models how policy parameters change as task parameters vary. The method identifies the number of charts that compose the manifold and then applies non-linear regression in each chart to construct a parameterized skill by predicting policy parameters from task parameters. We evaluate our method on an underactuated simulated robotic arm tasked with learning to accurately throw darts at a parameterized target location.

Learning Parameterized Skills

In this paper we introduce RL-CD, a method for solving reinforcement learning problems in non-stationary environments. The method is based on a mechanism for creating, updating and selecting one among several partial models of the environment. The partial models are incrementally built according to the system's capability of making predictions regarding a given sequence of observations. We propose, formalize and show the efficiency of this method both in a simple non-stationary environment and in a noisy scenario. We show that RL-CD performs better than two standard reinforcement learning algorithms and that it has advantages over methods specifically designed to cope with non-stationarity. Finally, we present known limitations of the method and future works.

/pdf/dealing-with-non-stationary-environments-using-context-4564bt4nkb.pdf

Dealing with non-stationary environments using context detection

Intelligent machines using machine learning algorithms are ubiquitous, ranging from simple data analysis and pattern recognition tools to complex systems that achieve superhuman performance on various tasks. Ensuring that they do not exhibit undesirable behavior-that they do not, for example, cause harm to humans-is therefore a pressing problem. We propose a general and flexible framework for designing machine learning algorithms. This framework simplifies the problem of specifying and regulating undesirable behavior. To show the viability of this framework, we used it to create machine learning algorithms that precluded the dangerous behavior caused by standard machine learning algorithms in our experiments. Our framework for designing machine learning algorithms simplifies the safe and responsible application of machine learning.

https://science.sciencemag.org/content/sci/366/6468/999.full.pdf

Preventing undesirable behavior of intelligent machines.

Learning in groups of traffic signals

Sound source localization is a well-researched subject with applications ranging from localizing sniper fire in urban battlefields to cataloging wildlife in rural areas. One critical application is the localization of noise pollution sources in urban environments, due to an increasing body of evidence linking noise pollution to adverse effects on human health. Current noise mapping techniques often fail to accurately identify noise pollution sources, because they rely on the interpolation of a limited number of scattered sound sensors. Aiming to produce accurate noise pollution maps, we developed the SoundCompass, a low-cost sound sensor capable of measuring local noise levels and sound field directionality. Our first prototype is composed of a sensor array of 52 Microelectromechanical systems (MEMS) microphones, an inertial measuring unit and a low-power field-programmable gate array (FPGA). This article presents the SoundCompass's hardware and firmware design together with a data fusion technique that exploits the sensing capabilities of the SoundCompass in a wireless sensor network to localize noise pollution sources. Live tests produced a sound source localization accuracy of a few centimeters in a 25-m2 anechoic chamber, while simulation results accurately located up to five broadband sound sources in a 10,000-m2 open field.

https://www.mdpi.com/1424-8220/14/2/1918/pdf

Bruno da Silva

Papers

Learning Parameterized Skills

Dealing with non-stationary environments using context detection

Preventing undesirable behavior of intelligent machines.

Learning in groups of traffic signals

SoundCompass: A Distributed MEMS Microphone Array-Based Sensor for Sound Source Localization