Andrew G. Barto’s research while affiliated with University of Massachusetts Amherst and other places

We study the problem of finding efficient exploration policies for the case in which an agent is momentarily not concerned with exploiting, and instead tries to compute a policy for later use. We first formally define the Optimal Exploration Problem as one of sequential sampling and show that its solutions correspond to paths of minimum expected length in the space of policies. We derive a model-free, local linear approximation to such solutions and use it to construct efficient exploration policies. We compare our model-free approach to other exploration techniques, including one with the best known PAC bounds, and show that ours is both based on a well-defined optimization problem and empirically efficient.

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.

Making well-behaved algorithms Machine learning algorithms are being used in an ever-increasing number of applications, and many of these applications affect quality of life. Yet such algorithms often exhibit undesirable behavior, from various types of bias to causing financial loss or delaying medical diagnoses. In standard machine learning approaches, the burden of avoiding this harmful behavior is placed on the user of the algorithm, who most often is not a computer scientist. Thomas et al. introduce a general framework for algorithm design in which this burden is shifted from the user to the designer of the algorithm. The researchers illustrate the benefits of their approach using examples in gender fairness and diabetes management. Science , this issue p. 999

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.

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. A reinforcement learning algorithm can be implemented on a hybrid analogue–digital platform based on memristive arrays for parallel and energy-efficient in situ training.

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.

Machine learning algorithms are everywhere, ranging from simple data analysis and pattern recognition tools used across the sciences to complex systems that achieve super-human performance on various tasks. Ensuring that they are well-behaved---that they do not, for example, cause harm to humans or act in a racist or sexist way---is therefore not a hypothetical problem to be dealt with in the future, but a pressing one that we address here. We propose a new framework for designing machine learning algorithms that simplifies the problem of specifying and regulating undesirable behaviors. To show the viability of this new framework, we use it to create new machine learning algorithms that preclude the sexist and harmful behaviors exhibited by standard machine learning algorithms in our experiments. Our framework for designing machine learning algorithms simplifies the safe and responsible application of machine learning.