Accelerating critic learning in approximate dynamic programming via value templates and perceptual learning

Shannon, T.T.; Santiago, R.A.; George, G.

doi:10.1109/ijcnn.2003.1224035

Cited by 4 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In paper [12], a method for accelerating DHP critic training using templates and perceptual learning was proposed. Both faster and more stable learning were achieved by using the value template and utilizing its inherent constraints to regularize the perceptual learning task.…”

Section: A Improvements Of Basic Methodsmentioning

confidence: 99%

A Survey of Approximate Dynamic Programming

Wang

Peng

Zhu

2009

2009 International Conference on Intelligent Human-Machine Systems and Cybernetics

View full text Add to dashboard Cite

Multi-stage decision problems under uncertainty are abundant in process industries. Markov decision process (MDP) is a general mathematical formulation of such problems. Whereas stochastic programming and dynamic programming are the standard methods to solve MDPs, their unwieldy computational requirements limit their usefulness in real applications. Approximate dynamic programming (ADP) combines simulation and function approximation to alleviate the "curse-of-dimensionality" associated with the traditional dynamic programming approach. In this paper, the method of ADP, which abates the curse-of-dimensionality by solving the DP within a carefully chosen, small subset of the state space, was introduced; a survey of recent research directions within the field of ADP had been made.

show abstract

Section: A Improvements Of Basic Methodsmentioning

confidence: 99%

A Survey of Approximate Dynamic Programming

Wang

Peng

Zhu

2009

2009 International Conference on Intelligent Human-Machine Systems and Cybernetics

View full text Add to dashboard Cite

show abstract

“…Sidarta and Ghaboussi (1998) [21] employed an artificial neural network model within a finite element analysis to extract the geo-material constitutive behavior from non-uniform material tests. Al-Rabadi, A.N., G. Lendaris, (2003) [22] used neural networks for representing the behavior of sand and clay soils. Ghaboussi and Sidarta (1998) [23] used neural networks to model both the drained and undrained behavior of sandy soil subjected to triaxial compression-type testing.…”

Section: Soil Properties and Behaviormentioning

confidence: 99%

Conjugate gradient neural network in prediction of clay behavior and parameters sensitivities

fard

2016

NMCE

View full text Add to dashboard Cite

The use of artificial neural networks has increased in many areas of engineering. In particular, this method has been applied to many geotechnical engineering problems and demonstrated some degree of success. A review of the literature reveals that it has been used successfully in modeling soil behavior, site characterization, earth retaining structures, settlement of structures, slope stability, design of tunnels and underground openings, liquefaction, soil permeability and hydraulic conductivity, soil compaction, soil swelling and classification of soils. The method of conjugate gradients provides a very effective way to optimize large, deterministic systems by gradient descent. In its standard form, however, it is not amenable to stochastic approximation of the gradient. Here we explore a number of ways to adopt ideas from conjugate gradient and Back Propagation in the stochastic setting, using fast Hessian-vector products to obtain curvature information effectively. In our benchmark experiments the resulting highly scalable algorithms converge about an order of magnitude faster than ordinary stochastic gradient descent. The objective of this paper is to provide a general view to describe this method in predicting mechanical behavior and constitutive modeling issues in geo-mechanical behavior of cohesive soil to be used in geo-mechanics. In this research the Batching Back Propagation method (BBP) has been employed and the characterized parameters are introduced as initial void ratio, liquid limit, plasticity index, natural density, moisture percent, solid density of grain, over consolidation ratio, and pre-consolidation pressure. The paper also intends to present how much the input memory may cover the accuracy of predicted behavior of standard triaxial drained and undrained tests. The paper also discusses the strengths and limitations of the proposed method compared to the other modeling approaches. Also, the sensitivity of intended parameters is investigated. D D

show abstract

“…Space limitations preclude surveying that literature here; a couple of accessible suggestions to the reader are [58], [62]. It is important to point out here that certain Fuzzy structures qualify as trainable universal function approximators, and thus, should in principle be usable in ADP processes.…”

Section: Pragmatic Aspects Of Employing Adpmentioning

confidence: 99%

A retrospective on Adaptive Dynamic Programming for control

Lendaris

2009

2009 International Joint Conference on Neural Networks

View full text Add to dashboard Cite

Some three decades ago, certain computational intelligence methods of reinforcement learning were recognized as implementing an approximation of Bellman's Dynamic Programming method, which is known in the controls community as an important tool for designing optimal control policies for nonlinear plants and sequential decision making. Significant theoretical and practical developments have occurred within this arena, mostly in the past decade, with the methodology now usually referred to as Adaptive Dynamic Programming (ADP). The objective of this paper is to provide a retrospective of selected threads of such developments. In addition, a commentary is offered concerning present status of ADP, and threads for future research and development within the controls field are suggested.

show abstract

Accelerating critic learning in approximate dynamic programming via value templates and perceptual learning

Cited by 4 publications

References 15 publications

A Survey of Approximate Dynamic Programming

A Survey of Approximate Dynamic Programming

Conjugate gradient neural network in prediction of clay behavior and parameters sensitivities

A retrospective on Adaptive Dynamic Programming for control

Contact Info

Product

Resources

About