This paper presents a model-based actorcritic algorithm in continuous time and space. Two function approximators are used: one learns the policy (the actor) and the other learns the state-value function (the critic). The critic learns with the TD(λ) algorithm and the actor by gradient ascent on the Hamiltonian. A similar algorithm had been proposed by Doya, but this one is more general. This al...

This paper sets out to explore the thinking and the direct and often indirect influence of the social theorist Philip Rieff on later generations of social theorists, especially in regard to the key sociological concept of community. It is argued that the work of this culturally-conservative social theorist has had a powerful, if somewhat shadowy, influence on such key radical critics of modern ...

This paper describes an intelligent computer-aided architectural design system (ICAAD) called ICADS. ICADS encapsulates different types of design knowledge into independent “critic” modules. Each “critic” module possesses expertise in evaluating an architect’s work in different areas of architectural design and can offer expert advice when needed. This research focuses on the representation of ...

Stochastic gradient descent (SGD), which updates the model parameters by adding a local gradient times a learning rate at each step, is widely used in model training of machine learning algorithms such as neural networks. It is observed that the models trained by SGD are sensitive to learning rates and good learning rates are problem specific. We propose an algorithm to automatically learn lear...

This study investigated learning style preferences among professional translators. The purposes of the study were to (a) find the prevailing learning style among the Iranian professional translators; (b) reveal any significant difference in the translators’ learning style preferences in terms of gender; and (c) find any significant difference between individual learning style and translation co...

The ability to learn at different resolutions in time may help overcome one of the main challenges in deep reinforcement learning — sample efficiency. Hierarchical agents that operate at different levels of temporal abstraction can learn tasks more quickly because they can divide the work of learning behaviors among multiple policies and can also explore the environment at a higher level. In th...