Funding from the U.S. Air Force and the National Science Foundation helped to reignite interest in reinforcement learning as a predominant approach to machine learning.

This retrospective describes the overall research project that gave rise to the authors' paper “Neuronlike adaptive elements that can solve difficult learning control problems” that was published in the 1983 Neural and Sensory Information Processing special issue of the IEEE Transactions on Systems, Man, and Cybernetics. This look back explains how this project came about, presents the ideas and previous publications that influenced it, and describes our most closely related subsequent research. It concludes by pointing out some noteworthy aspects of this article that have been eclipsed by its main contributions, followed by commenting on some of the directions and cautions that should inform future research.

EDITORIAL article Front. Neurorobot., 17 January 2020 Volume 13 - 2019 | https://doi.org/10.3389/fnbot.2019.00115

Reinforcement learning algorithms that use deep neural networks are a promising approach for the development of machines that can acquire knowledge and solve problems without human input or supervision. At present, however, these algorithms are implemented in software running on relatively standard complementary metal–oxide–semiconductor digital platforms, where performance will be constrained by the limits of Moore’s law and von Neumann architecture. Here, we report an experimental demonstration of reinforcement learning on a three-layer 1-transistor 1-memristor (1T1R) network using a modified learning algorithm tailored for our hybrid analogue–digital platform. To illustrate the capabilities of our approach in robust in situ training without the need for a model, we performed two classic control problems: the cart–pole and mountain car simulations. We also show that, compared with conventional digital systems in real-world reinforcement learning tasks, our hybrid analogue–digital computing system has the potential to achieve a significant boost in speed and energy efficiency.

This article focuses on the division of labor between evolution and development in solving sequential, state-dependent decision problems. Currently, behavioral ecologists tend to use dynamic programming methods to study such problems. These methods are successful at predicting animal behavior in a variety of contexts. However, they depend on a distinct set of assumptions. Here, we argue that behavioral ecology will benefit from drawing more than it currently does on a complementary collection of tools, called reinforcement learning methods. These methods allow for the study of behavior in highly complex environments, which conventional dynamic programming methods do not feasibly address. In addition, reinforcement learning methods are well-suited to studying how biological mechanisms solve developmental and learning problems. For instance, we can use them to study simple rules that perform well in complex environments. Or to investigate under what conditions natural selection favors fixed, non-plastic traits (which do not vary across individuals), cue-driven-switch plasticity (innate instructions for adaptive behavioral development based on experience), or developmental selection (the incremental acquisition of adaptive behavior based on experience). If natural selection favors developmental selection, which includes learning from environmental feedback, we can also make predictions about the design of reward systems. Our paper is written in an accessible manner and for a broad audience, though we believe some novel insights can be drawn from our discussion. We hope our paper will help advance the emerging bridge connecting the fields of behavioral ecology and reinforcement learning.

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.

The idea of implementing reinforcement learning in a computer was one of the earliest ideas about the possibility of AI, but reinforcement learning remained on the margin of AI until relatively recently. Today we see reinforcement learning playing essential roles in some of the most impressive AI applications. This article presents observations from the author’s personal experience with reinforcement learning over the most recent 40 years of its history in AI, focusing on striking connections that emerged between largely separate disciplines and on some of the findings that surprised him along the way. These connections and surprises place reinforcement learning in a historical context, and they help explain the success it is finding in modern AI. The article concludes by discussing some of the challenges that need to be faced as reinforcement learning moves out into real world.

The increased demand for renewable energy and the development of energy independent building designs have motivated significant research into the improvement of wind power technologies that target urban environments. However, the implementation of wind turbines in urban environments is still very limited. There have been some studies analyzing different designs of urban wind turbines either using computational fluid dynamics (CFD), wind tunnel tests or field data for existing or new turbine designs. This paper reviews the state-of-the-art of urban wind energy by examining the various types of urban wind turbine designs, with a view to understand their performance and the synergy between the turbines and the urban environments. It also considers a flanged diffuser shroud mechanism - a fluid machine, mounted on rooftop of buildings used as casing for small wind turbines to improve turbine performance by using mainly CFD. The diffuser shroud mechanism can draw the airflow over buildings utilizing its special features such as, cycloidal curve geometry at the inlet and a vortex generating flange at the outlet, to guide and accelerate the airflow inside. The performance of the fluid machine is optimized parametrically. The mechanism is modeled on a building rooftop in a real test site in Montreal, Canada with real statistical wind data. The CFD result confirms the functionality of the fluid machine to take advantage of the airflow over buildings in complex built-environments for wind power generation.