Behavior learning of a face robot based on the characteristics of human instruction

Computer simulation experiments were performed to examine the effectiveness of OR- and comparative-reinforcement learning algorithms. In the simulation, human rewards were given as +1 and -1. Two models of human instruction that determine which reward is to be given in every step of a human instruction were used. Results show that human instruction may have a possibility of including both model-A and model-B characteristics, and it can be expected that the comparative-reinforcement learning algorithm is more effective for learning by human instructions.

Computer-based selection of joining processes

The assembly of any manufactured product involves joining. This paper describes ways of selecting processes for joining. The method allows discrimination of the joint geometry, joint loading, material, and other attributes of the joint itself, identifying the subset of available processes capable of meeting a given set of design constraints. A relational database containing data-tables for joining processes, materials to be joined, and joint geometry and mode of loading, allows the attributes of each of these to be stored in an appropriate format, and permits links to be created between those that are related. A search engine isolates the processes that meet design requirements on material, joint geometry and loading. The method is illustrated in Part 2 by case studies, utilising software that embodies the method.

Proceedings of an international workshop on the value of computer-based engineering tools, held in Cambridge in April 1997

There is increasing adoption of computer-based tools to support the product development process. Tolls include computer-aided design, computer-aided manufacture, systems engineering and product data management systems. The fact that companies choose to invest in tools might be regarded as evidence that tools, in aggregate, are perceived to possess business value through their application to engineering activities. Yet the ways in which value accrues from tool technology are poorly understood.

This report records the proceedings of an international workshop during which some novel approaches to improving our understanding of this problem of tool valuation were presented and debated. The value of methods and processes were also discussed. The workshop brought together British, Dutch, German and Italian researchers. The presenters included speakers from industry and academia (the University of Cambridge, the University of Magdeburg and the Politechnico de Torino)

The work presented showed great variety. Research methods include case studies, questionnaires, statistical analysis, semi-structured interviews, deduction, inductive reasoning, the recording of anecdotes and analogies. The presentations drew on financial investment theory, the industrial experience of workshop participants, discussions with students developing tools, modern economic theories and speculation on the effects of company capabilities.

Probabilistic inference for fast learning in control

A novel framework is provided for very fast model-based reinforcement learning in continuous state and action spaces. It requires probabilistic models that explicitly characterize their levels of condence. Within the framework, exible, non-parametric models are used to describe the world based on previously collected experience. It demonstrates learning on the cart-pole problem in a setting where very limited prior knowledge about the task has been provided. Learning progressed rapidly, and a good policy found after only a small number of iterations.

Model based learning of sigma points in unscented Kalman filtering

The unscented Kalman filter (UKF) is a widely used method in control and time series applications. The UKF suffers from arbitrary parameters necessary for a step known as sigma point placement, causing it to perform poorly in nonlinear problems. We show how to treat sigma point placement in a UKF as a learning problem in a model based view. We demonstrate that learning to place the sigma points correctly from data can make sigma point collapse much less likely. Learning can result in a significant increase in predictive performance over default settings of the parameters in the UKF and other filters designed to avoid the problems of the UKF, such as the GP-ADF. At the same time, we maintain a lower computational complexity than the other methods. We call our method UKF-L. ©2010 IEEE.

Model based learning of sigma points in unscented Kalman filtering

The unscented Kalman filter (UKF) is a widely used method in control and time series applications. The UKF suffers from arbitrary parameters necessary for sigma point placement, potentially causing it to perform poorly in nonlinear problems. We show how to treat sigma point placement in a UKF as a learning problem in a model based view. We demonstrate that learning to place the sigma points correctly from data can make sigma point collapse much less likely. Learning can result in a significant increase in predictive performance over default settings of the parameters in the UKF and other filters designed to avoid the problems of the UKF, such as the GP-ADF. At the same time, we maintain a lower computational complexity than the other methods. We call our method UKF-L. © 2011 Elsevier B.V.

Altruistic learning.

The origin of altruism remains one of the most enduring puzzles of human behaviour. Indeed, true altruism is often thought either not to exist, or to arise merely as a miscalculation of otherwise selfish behaviour. In this paper, we argue that altruism emerges directly from the way in which distinct human decision-making systems learn about rewards. Using insights provided by neurobiological accounts of human decision-making, we suggest that reinforcement learning in game-theoretic social interactions (habitisation over either individuals or games) and observational learning (either imitative of inference based) lead to altruistic behaviour. This arises not only as a result of computational efficiency in the face of processing complexity, but as a direct consequence of optimal inference in the face of uncertainty. Critically, we argue that the fact that evolutionary pressure acts not over the object of learning ('what' is learned), but over the learning systems themselves ('how' things are learned), enables the evolution of altruism despite the direct threat posed by free-riders.