Journal ArticleDOI
Neuronlike adaptive elements that can solve difficult learning control problems
Andrew G. Barto,Richard S. Sutton,Charles W. Anderson +2 more
- Vol. 13, Iss: 5, pp 834-846
TLDR
In this article, a system consisting of two neuron-like adaptive elements can solve a difficult learning control problem, where the task is to balance a pole that is hinged to a movable cart by applying forces to the cart base.Abstract:
It is shown how a system consisting of two neuronlike adaptive elements can solve a difficult learning control problem. The task is to balance a pole that is hinged to a movable cart by applying forces to the cart's base. It is argued that the learning problems faced by adaptive elements that are components of adaptive networks are at least as difficult as this version of the pole-balancing problem. The learning system consists of a single associative search element (ASE) and a single adaptive critic element (ACE). In the course of learning to balance the pole, the ASE constructs associations between input and output by searching under the influence of reinforcement feedback, and the ACE constructs a more informative evaluation function than reinforcement feedback alone can provide. The differences between this approach and other attempts to solve problems using neurolike elements are discussed, as is the relation of this work to classical and instrumental conditioning in animal learning studies and its possible implications for research in the neurosciences.read more
Citations
More filters
Journal ArticleDOI
Striatal dopamine in motor activation and reward-mediated learning : steps towards a unifying model
TL;DR: The existence of separate populations of dopamine receptors, differentially modulating cholinergic and glutamatergic synapses, suggests a possible resolution of the paradox of dopamine inhibition and reward-mediated learning.
Proceedings Article
Temporal Difference Learning of Position Evaluation in the Game of Go
TL;DR: This work demonstrates a viable alternative by training networks to evaluate Go positions via temporal difference (TD) learning, based on network architectures that reflect the spatial organization of both input and reinforcement signals on the Go board, and training protocols that provide exposure to competent (though unlabelled) play.
Proceedings ArticleDOI
Automated fuzzy knowledge base generation and tuning
TL;DR: An approach to generating and tuning a knowledge base for fuzzy logic control (FLC) of an inverted pendulum using a modified self-organizing control procedure under typical FLC design choices with a very crude plant model to quickly converge on a rule base appropriate for the plant.
Journal ArticleDOI
Efficient reinforcement learning using recursive least-squares methods
Xin Xu,Han-gen He,Dewen Hu +2 more
TL;DR: RLS methods are used to solve reinforcement learning problems, where two new reinforcement learning algorithms using linear value function approximators are proposed and analyzed and it is shown that the data efficiency of learning control can also be improved by using RLS methods in the learning-prediction process of the critic.
Journal ArticleDOI
A systematic classification of neural-network-based control
TL;DR: This work breaks the available schemes down to their essential functional features and organizes the latter into a multi-level classification, revealing that similar schemes often get placed in different categories, fundamentally different features often get lumped into a single category and proposed new schemes are often merely permutations and combinations of the well-established fundamental features.
References
More filters
Journal ArticleDOI
Receptive fields, binocular interaction and functional architecture in the cat's visual cortex
David H. Hubel,Torsten N. Wiesel +1 more
TL;DR: This method is used to examine receptive fields of a more complex type and to make additional observations on binocular interaction and this approach is necessary in order to understand the behaviour of individual cells, but it fails to deal with the problem of the relationship of one cell to its neighbours.
Journal ArticleDOI
A Theory of Cerebellar Cortex
TL;DR: A detailed theory of cerebellar cortex is proposed whose consequence is that the cerebellum learns to perform motor skills and two forms of input—output relation are described, both consistent with the cortical theory.
Journal ArticleDOI
Receptive fields and functional architecture in two nonstriate visual areas (18 and 19) of the cat.
David H. Hubel,Torsten N. Wiesel +1 more
TL;DR: To UNDERSTAND VISION in physiological terms represents a formidable problem for the biologist, and one approach is to stimulate the retina with patterns of light while recording from single cells or fibers at various points along the visual pathway.
Journal ArticleDOI
Toward a modern theory of adaptive networks: Expectation and prediction.
TL;DR: The adaptive element presented learns to increase its response rate in anticipation of increased stimulation, producing a conditioned response before the occurrence of the unconditioned stimulus, and is in strong agreement with the behavioral data regarding the effects of stimulus context.
Journal ArticleDOI
Steps toward Artificial Intelligence
TL;DR: The problems of heuristic programming can be divided into five main areas: Search, Pattern-Recognition, Learning, Planning, and Induction as discussed by the authors, and the most successful heuristic (problem-solving) programs constructed to date.