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
Proceedings Article
Exploiting Model Uncertainty Estimates for Safe Dynamic Control Learning
TL;DR: This paper addresses the case where the system must be prevented from having catastrophic failures during learning, and proposes a new algorithm adapted from the dual control literature and use Bayesian locally weighted regression models with dynamic programming.
Journal ArticleDOI
A developmental model for the evolution of artificial neural networks
J. C. Astor,Christoph Adami +1 more
TL;DR: In this paper, a model of decentralized growth and development for artificial neural networks (ANNs), inspired by developmental biology and the physiology of nervous systems, is presented, where each individual artificial neuron is an autonomous unit whose behavior is determined only by the genetic information it harbors and local concentrations of substrates.
Reinforcement Learning Through Gradient Descent
TL;DR: In addition to better convergence properties, it is shown how gradient descent allows an inelegant, inconvenient algorithm like Advantage updating to be converted into a much simpler and more easily analyzed algorithmlike Advantage learning.
Journal ArticleDOI
Curiosity driven reinforcement learning for motion planning on humanoids
TL;DR: This work embodies a curious agent in the complex iCub humanoid robot, the first ever embodied, curious agent for real-time motion planning on a humanoid, and demonstrates that it can learn compact Markov models to represent large regions of the iCub's configuration space.
Posted Content
MOPO: Model-based Offline Policy Optimization
Tianhe Yu,Garrett Thomas,Lantao Yu,Stefano Ermon,James Zou,Sergey Levine,Chelsea Finn,Tengyu Ma +7 more
TL;DR: A new model-based offline RL algorithm is proposed that applies the variance of a Lipschitz-regularized model as a penalty to the reward function, and it is found that this algorithm outperforms both standard model- based RL methods and existing state-of-the-art model-free offline RL approaches on existing offline RL benchmarks, as well as two challenging continuous control tasks.
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.