There have been numerous attempts in explaining the general learning behaviours by various cognitive models. Multiple hypotheses have been put further to qualitatively argue the best-fit model for motor skill acquisition task and its variations. In this context, for a discrete sequence production (DSP) task, one of the most insightful models is Verwey's Dual Processor Model (DPM). It largely explains the learning and behavioural phenomenon of skilled discrete key-press sequences without providing any concrete computational basis of reinforcement. Therefore, we propose a quantitative explanation for Verwey's DPM hypothesis by experimentally establishing a general computational framework for motor skill learning. We attempt combining the qualitative and quantitative theories based on a best-fit model of the experimental simulations of variations of dual processor models. The fundamental premise of sequential decision making for skill learning is based on interacting model-based (MB) and model-free (MF) reinforcement learning (RL) processes. Our unifying framework shows the proposed idea agrees well to Verwey's DPM and Fitts' three phases of skill learning. The accuracy of our model can further be validated by its statistical fit with the human-generated data on simple environment tasks like the grid-world.

Programming a robot to deal with open-ended tasks remains a challenge, in particular if the robot has to manipulate objects. Launching, grasping, pushing or any other object interaction can be simulated but the corresponding models are not reversible and the robot behavior thus cannot be directly deduced. These behaviors are hard to learn without a demonstration as the search space is large and the reward sparse. We propose a method to autonomously generate a diverse repertoire of simple object interaction behaviors in simulation. Our goal is to bootstrap a robot learning and development process with limited informations about what the robot has to achieve and how. This repertoire can be exploited to solve different tasks in reality thanks to a proposed adaptation method or could be used as a training set for data-hungry algorithms. The proposed approach relies on the definition of a goal space and generates a repertoire of trajectories to reach attainable goals, thus allowing the robot to control this goal space. The repertoire is built with an off-the-shelf simulation thanks to a quality diversity algorithm. The result is a set of solutions tested in simulation only. It may result in two different problems: (1) as the repertoire is discrete and finite, it may not contain the trajectory to deal with a given situation or (2) some trajectories may lead to a behavior in reality that differs from simulation because of a reality gap. We propose an approach to deal with both issues by using a local linearization between the motion parameters and the observed effects. Furthermore, we present an approach to update the existing solution repertoire with the tests done on the real robot. The approach has been validated on two different experiments on the Baxter robot: a ball launching and a joystick manipulation tasks.

Swarm control is a difficult problem due to the need to guide a large number of agents simultaneously. We cast the problem as a shepherding problem, similar to biological dogs guiding a group of sheep towards a goal. The shepherd needs to deal with complex and dynamic environments and make decisions in order to direct the swarm from one location to another. In this paper, we design a novel curriculum to teach an artificial intelligence empowered agent to shepherd in the presence of the large state space associated with the shepherding problem and in a transparent manner. The results show that a properly designed curriculum could indeed enhance the speed of learning and the complexity of learnt behaviours.

The design of reward functions in reinforcement learning is a human skill that comes with experience. Unfortunately, there is not any methodology in the literature that could guide a human to design the reward function or to allow a human to transfer the skills developed in designing reward functions to another human and in a systematic manner. In this paper, we use Systematic Instructional Design, an approach in human education, to engineer a machine education methodology to design reward functions for reinforcement learning. We demonstrate the methodology in designing a hierarchical genetic reinforcement learner that adopts a neural network representation to evolve a swarm controller for an agent shepherding a boids-based swarm. The results reveal that the methodology is able to guide the design of hierarchical reinforcement learners, with each model in the hierarchy learning incrementally through a multi-part reward function. The hierarchy acts as a decision fusion function that combines the individual behaviours and skills learnt by each instruction to create a smart shepherd to control the swarm.

Terms like "machine learning," "deep learning," "neural networks," "artificial intelligence" or "A.I.," "data science," and more have been the buzzwords of the last few years in technology. Because of advances in computing power and an increase in the amount of data available, techniques that have been known about for decades can now be put into meaningful practice. But what do they actually mean? Most of us are aware of the 10,000-foot explanation along the lines of "It's all about teaching computers to solve problems for us," but many people probably aren't aware of what is actually going on under the hood. The basics of machine learning are simple enough, intuitive enough, and, more importantly, interesting enough to be picked up by anyone in a relatively short amount of time.

The first thing people think of when they hear the term "Machine Learning" goes a little something like the Matrix. All around, there are computers taking over the world, let alone the human race. In any case, people generally just want nothing to do with it. What if I told you those people don't even know what machine learning and things like backpropagation really are? Then you can go back to worrying about the robot-led apocalypse that's supposed to happen next Friday.

The advancements in the development of artificial intelligence spread all over the world at a tremendous speed and create an incredible hype increasing our expectations. As a matter of fact, it is rather difficult to disappoint a user in an entertaining domain: an introduction of AI and neural networks is instantly gaining immense popularity (Prisma and FaceApp applications are good examples of that). In this article, we have compiled 9 ways to use artificial intelligence in education. Automated grading is a specialized AI based computer program that simulates the behavior of a teacher to assign grades to essays written in an educational setting. It can assess students' knowledge, analyzing their answers, giving feedback and making personalized training plans.

Artificial intelligence is cast all at once as the technology that will save the world and end it. To cut through the noise and hype, VentureBeat spoke with luminaries whose views on the right way to do AI have been informed by years of working with some of the biggest tech and industry companies on the planet. Below find insights from Google Brain cofounder Andrew Ng, Cloudera general manager of ML and Fast Forward Labs founder Hilary Mason, Facebook AI Research founder Yann LeCun, and Accenture's responsible AI global lead Dr. Rumman Chowdhury. We wanted to get a sense of what they saw as the key milestones of 2018 and hear what they think is in store for 2019. Amid a recap of the year and predictions for the future, some said they were encouraged to be hearing fewer Terminator AI apocalypse scenarios, as more people understand what AI can and cannot do.

"With the growing interest in complex adaptive systems, artificial life, swarms and simulated societies, the concept of "collective intelligence" is coming more and more to the fore. The basic idea is that a group of individuals (e.g. Complex, apparently intelligent behavior may emerge from the synergy created by simple interactions between individuals that follow simple rules." A collective mental map is developed basically by superposing a number of individual mental maps. There must be sufficient diversity among these individual maps to cover an as large as possible domain, yet sufficient redundancy so that the overlap between maps is large enough to make the resulting graph fully connected, and so that each preference in the map is the superposition of a number of individual preferences that is large enough to cancel out individual fluctuations.

First, if you combine what you already know about your clients with data on the products and services each client has, then you can use machine learning to build a predictor of need. For example, if clients A, B, and C all have a need for product X, and client D looks very similar to clients A, B, and C, then it's a good bet that client D needs product X, too. This is a classic supervised learning problem: You train an algorithm based on known outcomes (clients A, B, and C have product X), and then use the resulting model to predict the need for product X among the clients who do not have that product.