Neural Comput - Toward nonlinear local reinforcement learning rules through neuroevolution.

Tópicos

{ problem(2511) optim(1539) algorithm(950) }
{ system(1976) rule(880) can(841) }
{ network(2748) neural(1063) input(814) }
{ perform(999) metric(946) measur(919) }
{ state(1844) use(1261) util(961) }
{ control(1307) perform(991) simul(935) }
{ inform(2794) health(2639) internet(1427) }
{ take(945) account(800) differ(722) }
{ model(3480) simul(1196) paramet(876) }
{ method(984) reconstruct(947) comput(926) }
{ use(1733) differ(960) four(931) }
{ design(1359) user(1324) use(1319) }
{ featur(1941) imag(1645) propos(1176) }
{ case(1353) use(1143) diagnosi(1136) }
{ can(981) present(881) function(850) }
{ activ(1452) weight(1219) physic(1104) }
{ sequenc(1873) structur(1644) protein(1328) }
{ imag(2675) segment(2577) method(1081) }
{ assess(1506) score(1403) qualiti(1306) }
{ concept(1167) ontolog(924) domain(897) }
{ clinic(1479) use(1117) guidelin(835) }
{ method(1557) propos(1049) approach(1037) }
{ data(1714) softwar(1251) tool(1186) }
{ general(901) number(790) one(736) }
{ risk(3053) factor(974) diseas(938) }
{ ehr(2073) health(1662) electron(1139) }
{ research(1218) medic(880) student(794) }
{ cost(1906) reduc(1198) effect(832) }
{ group(2977) signific(1463) compar(1072) }
{ data(3008) multipl(1320) sourc(1022) }
{ first(2504) two(1366) second(1323) }
{ intervent(3218) particip(2042) group(1664) }
{ analysi(2126) use(1163) compon(1037) }
{ use(976) code(926) identifi(902) }
{ drug(1928) target(777) effect(648) }
{ estim(2440) model(1874) function(577) }
{ model(3404) distribut(989) bayesian(671) }
{ can(774) often(719) complex(702) }
{ imag(1947) propos(1133) code(1026) }
{ data(1737) use(1416) pattern(1282) }
{ measur(2081) correl(1212) valu(896) }
{ imag(1057) registr(996) error(939) }
{ bind(1733) structur(1185) ligand(1036) }
{ method(1219) similar(1157) match(930) }
{ featur(3375) classif(2383) classifi(1994) }
{ imag(2830) propos(1344) filter(1198) }
{ patient(2315) diseas(1263) diabet(1191) }
{ studi(2440) review(1878) systemat(933) }
{ motion(1329) object(1292) video(1091) }
{ treatment(1704) effect(941) patient(846) }
{ surgeri(1148) surgic(1085) robot(1054) }
{ framework(1458) process(801) describ(734) }
{ error(1145) method(1030) estim(1020) }
{ chang(1828) time(1643) increas(1301) }
{ learn(2355) train(1041) set(1003) }
{ algorithm(1844) comput(1787) effici(935) }
{ extract(1171) text(1153) clinic(932) }
{ model(2220) cell(1177) simul(1124) }
{ care(1570) inform(1187) nurs(1089) }
{ search(2224) databas(1162) retriev(909) }
{ howev(809) still(633) remain(590) }
{ data(3963) clinic(1234) research(1004) }
{ studi(1410) differ(1259) use(1210) }
{ research(1085) discuss(1038) issu(1018) }
{ system(1050) medic(1026) inform(1018) }
{ import(1318) role(1303) understand(862) }
{ model(2341) predict(2261) use(1141) }
{ visual(1396) interact(850) tool(830) }
{ compound(1573) activ(1297) structur(1058) }
{ perform(1367) use(1326) method(1137) }
{ studi(1119) effect(1106) posit(819) }
{ blood(1257) pressur(1144) flow(957) }
{ spatial(1525) area(1432) region(1030) }
{ record(1888) medic(1808) patient(1693) }
{ health(3367) inform(1360) care(1135) }
{ monitor(1329) mobil(1314) devic(1160) }
{ patient(2837) hospit(1953) medic(668) }
{ model(2656) set(1616) predict(1553) }
{ data(2317) use(1299) case(1017) }
{ age(1611) year(1155) adult(843) }
{ medic(1828) order(1363) alert(1069) }
{ signal(2180) analysi(812) frequenc(800) }
{ sampl(1606) size(1419) use(1276) }
{ gene(2352) biolog(1181) express(1162) }
{ activ(1138) subject(705) human(624) }
{ time(1939) patient(1703) rate(768) }
{ patient(1821) servic(1111) care(1106) }
{ use(2086) technolog(871) perceiv(783) }
{ health(1844) social(1437) communiti(874) }
{ structur(1116) can(940) graph(676) }
{ high(1669) rate(1365) level(1280) }
{ cancer(2502) breast(956) screen(824) }
{ result(1111) use(1088) new(759) }
{ implement(1333) system(1263) develop(1122) }
{ survey(1388) particip(1329) question(1065) }
{ decis(3086) make(1611) patient(1517) }
{ process(1125) use(805) approach(778) }
{ method(1969) cluster(1462) data(1082) }
{ method(2212) result(1239) propos(1039) }
{ detect(2391) sensit(1101) algorithm(908) }

Resumo

We consider the problem of designing local reinforcement learning rules for artificial neural network (ANN) controllers. Motivated by the universal approximation properties of ANNs, we adopt an ANN representation for the learning rules, which are optimized using evolutionary algorithms. We evaluate the ANN rules in partially observable versions of four tasks: the mountain car, the acrobot, the cart pole balancing, and the nonstationary mountain car. For testing whether such evolved ANN-based learning rules perform satisfactorily, we compare their performance with the performance of SARSA() with tile coding, when the latter is provided with either full or partial state information. The comparison shows that the evolved rules perform much better than SARSA() with partial state information and are comparable to the one with full state information, while in the case of the nonstationary environment, the evolved rule is much more adaptive. It is therefore clear that the proposed approach can be particularly effective in both partially observable and nonstationary environments. Moreover, it could potentially be utilized toward creating more general rules that can be applied in multiple domains and transfer learning scenarios.

Resumo Limpo

consid problem design local reinforc learn rule artifici neural network ann control motiv univers approxim properti ann adopt ann represent learn rule optim use evolutionari algorithm evalu ann rule partial observ version four task mountain car acrobot cart pole balanc nonstationari mountain car test whether evolv annbas learn rule perform satisfactorili compar perform perform sarsa tile code latter provid either full partial state inform comparison show evolv rule perform much better sarsa partial state inform compar one full state inform case nonstationari environ evolv rule much adapt therefor clear propos approach can particular effect partial observ nonstationari environ moreov potenti util toward creat general rule can appli multipl domain transfer learn scenario

Resumos Similares

IEEE Trans Vis Comput Graph - Drawing and Labeling High-Quality Metro Maps by Mixed-Integer Programming. ( 0,69339853909322 )
IEEE Trans Neural Netw Learn Syst - Actor-critic-based optimal tracking for partially unknown nonlinear discrete-time systems. ( 0,673480728964066 )
IEEE Trans Neural Netw Learn Syst - Distributed Containment Control for Multiple Unknown Second-Order Nonlinear Systems With Application to Networked Lagrangian Systems. ( 0,668110739118206 )
IEEE Trans Neural Netw Learn Syst - Reinforcement learning design-based adaptive tracking control with less learning parameters for nonlinear discrete-time MIMO systems. ( 0,653586861238704 )
IEEE Trans Neural Netw Learn Syst - Adaptive Control of Uncertain Nonaffine Nonlinear Systems With Input Saturation Using Neural Networks. ( 0,646791259126593 )
Comput Math Methods Med - Robust synchronization of delayed chaotic FitzHugh-Nagumo neurons under external electrical stimulation. ( 0,635431019171464 )
IEEE Trans Neural Netw Learn Syst - Randomized gradient-free method for multiagent optimization over time-varying networks. ( 0,612222281846175 )
IEEE Trans Neural Netw Learn Syst - Finite-Horizon Approximate Optimal Guaranteed Cost Control of Uncertain Nonlinear Systems With Application to Mars Entry Guidance. ( 0,605930581724723 )
Neural Comput - A DC programming approach for finding communities in networks. ( 0,603890944401595 )
IEEE Trans Image Process - An iterative L1-based image restoration algorithm with an adaptive parameter estimation. ( 0,601089924126183 )
Comput Math Methods Med - A 3D finite-difference BiCG iterative solver with the Fourier-Jacobi preconditioner for the anisotropic EIT/EEG forward problem. ( 0,600244778616239 )
IEEE Trans Neural Netw Learn Syst - Adaptive neural control of nonlinear MIMO systems with time-varying output constraints. ( 0,599344565855922 )
IEEE Trans Image Process - Fine-granularity and spatially-adaptive regularization for projection-based image deblurring. ( 0,596979694345006 )
Comput Math Methods Med - Optimal control of HIV dynamic using embedding method. ( 0,589901366836034 )
Int J Neural Syst - Optimal sparse approximation with integrate and fire neurons. ( 0,585382769620262 )
IEEE Trans Pattern Anal Mach Intell - Shape Representation and Registration in Vector Implicit Spaces: Adopting a Closed Form Solution in the Optimization Process. ( 0,581386474368748 )
Neural Comput - A self-organized neural comparator. ( 0,581021958318319 )
Comput. Biol. Med. - A synergic simulation-optimization approach for analyzing biomolecular dynamics in living organisms. ( 0,580061570274824 )
IEEE Trans Neural Netw Learn Syst - Missile Guidance Law Based on Robust Model Predictive Control Using Neural-Network Optimization. ( 0,579133852273597 )
IEEE Trans Image Process - Variational region-based segmentation using multiple texture statistics. ( 0,57854662658482 )
Int J Neural Syst - Indirect adaptive control of nonlinear systems based on bilinear neuro-fuzzy approximation. ( 0,577979415747609 )
IEEE Trans Pattern Anal Mach Intell - Polynomial Eigenvalue Solutions to Minimal Problems in Computer Vision. ( 0,577978228498194 )
J Biomed Inform - A PSO-based rule extractor for medical diagnosis. ( 0,577811841763701 )
IEEE Trans Neural Netw Learn Syst - On Equivalence of FIS and ELM for Interpretable Rule-Based Knowledge Representation. ( 0,577435512357675 )
IEEE Trans Pattern Anal Mach Intell - A Closed-Form Solution to Retinex with Nonlocal Texture Constraints. ( 0,57455909853066 )
IEEE Trans Neural Netw Learn Syst - Optoelectronic Systems Trained With Backpropagation Through Time. ( 0,573357992124944 )
Comput Math Methods Med - Fuzzy modeling and control of HIV infection. ( 0,572895376857326 )
IEEE Trans Image Process - Generalized inverse-approach model for spectral-signal recovery. ( 0,567626313787324 )
IEEE Trans Neural Netw Learn Syst - Further result on guaranteed H8 performance state estimation of delayed static neural networks. ( 0,566697666361252 )
Neural Comput - Simple modification of Oja rule limits L1-norm of weight vector and leads to sparse connectivity. ( 0,564180323624896 )
Neural Comput - Information-theoretic semi-supervised metric learning via entropy regularization. ( 0,564144944371141 )
IEEE Trans Neural Netw Learn Syst - Stochastic Stability of Delayed Neural Networks With Local Impulsive Effects. ( 0,563271974516146 )
IEEE Trans Neural Netw Learn Syst - Dynamic Surface Control Using Neural Networks for a Class of Uncertain Nonlinear Systems With Input Saturation. ( 0,563069945857558 )
Neural Comput - Regularized variational Bayesian learning of echo state networks with delay&sum readout. ( 0,561869263164091 )
IEEE Trans Neural Netw Learn Syst - A Neurodynamic Optimization Method for Recovery of Compressive Sensed Signals With Globally Converged Solution Approximating to l0 Minimization. ( 0,561082124371048 )
IEEE Trans Neural Netw Learn Syst - Convergence and rate analysis of neural networks for sparse approximation. ( 0,558958577843687 )
IEEE Trans Image Process - Gradient-based image recovery methods from incomplete Fourier measurements. ( 0,558483886951222 )
J. Comput. Biol. - An improved satisfiability algorithm for nested canalyzing functions and its application to determining a singleton attractor of a Boolean network. ( 0,556945687805263 )
Neural Comput - Insights from a simple expression for linear fisher information in a recurrently connected population of spiking neurons. ( 0,554432244595069 )
Comput Math Methods Med - Optimal control of the lost to follow up in a tuberculosis model. ( 0,553711155946678 )
IEEE Trans Image Process - Geodesic active fields--a geometric framework for image registration. ( 0,552827433957086 )
IEEE Trans Pattern Anal Mach Intell - Higher-Dimensional Affine Registration and Vision Applications. ( 0,551194461894427 )
Comput Math Methods Med - Sparse reconstruction for bioluminescence tomography based on the semigreedy method. ( 0,548175085768223 )
IEEE Trans Pattern Anal Mach Intell - Secure and Robust Iris Recognition Using Random Projections and Sparse Representations. ( 0,545856734566776 )
Med Biol Eng Comput - Experimental comparison of connectivity measures with simulated EEG signals. ( 0,545036965953967 )
IEEE Trans Image Process - Distance regularized level set evolution and its application to image segmentation. ( 0,544694323512652 )
IEEE Trans Neural Netw Learn Syst - Adaptive Neural Control of Nonaffine Systems With Unknown Control Coefficient and Nonsmooth Actuator Nonlinearities. ( 0,544109700173419 )
IEEE Trans Vis Comput Graph - ViSizer: A Visualization Resizing Framework. ( 0,543494131655022 )
IEEE Trans Image Process - Smoothed low rank and sparse matrix recovery by iteratively reweighted least squares minimization. ( 0,543098139449249 )
J. Comput. Biol. - Comparing pedigree graphs. ( 0,542780352661365 )
IEEE Trans Neural Netw Learn Syst - Incremental Support Vector Learning for Ordinal Regression. ( 0,540056321305131 )
Neural Comput - A parallel dual matrix method for blind signal separation. ( 0,537765581677919 )
IEEE Trans Image Process - Fitting multiple connected ellipses to an image silhouette hierarchically. ( 0,537636247573495 )
Comput Math Methods Med - Regularized multidirections and multiscales anisotropic diffusion for sinogram restoration of low-dosed computed tomography. ( 0,535607986108209 )
IEEE Trans Image Process - Coupled variational image decomposition and restoration model for blurred cartoon-plus-texture images with missing pixels. ( 0,535089583227367 )
Comput Biol Chem - A hyper-heuristic for the Longest Common Subsequence problem. ( 0,534231994057722 )
Neural Comput - Characterization of minimum error linear coding with sensory and neural noise. ( 0,533533718319154 )
Neural Comput - Nondegenerate piecewise linear systems: a finite Newton algorithm and applications in machine learning. ( 0,532518476866322 )
IEEE Trans Image Process - High-quality reflection separation using polarized images. ( 0,531827091795189 )
IEEE Trans Image Process - Hessian Schatten-norm regularization for linear inverse problems. ( 0,531628240753728 )
Comput Math Methods Med - Variational principles for buckling of microtubules modeled as nonlocal orthotropic shells. ( 0,530672621880413 )
IEEE Trans Neural Netw Learn Syst - Adaptive Output-Feedback Neural Control of Switched Uncertain Nonlinear Systems With Average Dwell Time. ( 0,530561329724258 )
IEEE Trans Image Process - Box relaxation schemes in staggered discretizations for the dual formulation of total variation minimization. ( 0,529430847764903 )
IEEE Trans Neural Netw Learn Syst - Passivity and Passification of Memristor-Based Recurrent Neural Networks With Additive Time-Varying Delays. ( 0,528597444899331 )
IEEE Trans Neural Netw Learn Syst - Is extreme learning machine feasible? A theoretical assessment (part I). ( 0,528590015508472 )
J Med Syst - ACO for the surgical cases assignment problem. ( 0,528573212612755 )
IEEE Trans Image Process - Practical bounds on image denoising: from estimation to information. ( 0,527636400618185 )
IEEE Trans Image Process - Restoration of Poissonian images using alternating direction optimization. ( 0,526443885213882 )
Neural Comput - Finding the event structure of neuronal spike trains. ( 0,525747331339168 )
Neural Comput - Natural gradient learning algorithms for RBF networks. ( 0,525674723818811 )
Neural Comput - Neural relax. ( 0,524055776089376 )
IEEE Trans Pattern Anal Mach Intell - Robust Visual Tracking Using Local Sparse Appearance Model and K-Selection. ( 0,52289070161128 )
IEEE Trans Image Process - Parameter selection for total-variation-based image restoration using discrepancy principle. ( 0,522855678156115 )
IEEE Trans Image Process - Computing steerable principal components of a large set of images and their rotations. ( 0,522251721856573 )
IEEE Trans Neural Netw Learn Syst - Discrete-Time Zhang Neural Network for Online Time-Varying Nonlinear Optimization With Application to Manipulator Motion Generation. ( 0,522144522144522 )
IEEE Trans Image Process - Efficient variational Bayesian approximation method based on subspace optimization. ( 0,521979673316571 )
IEEE Trans Pattern Anal Mach Intell - Minimum Near-Convex Shape Decomposition. ( 0,521160225707106 )
IEEE Trans Image Process - Simultaneous segmentation and multiresolution nonrigid atlas registration. ( 0,519793869230455 )
Neural Comput - Alternating proximal regularized dictionary learning. ( 0,517875583607968 )
J Med Syst - Cost and performance: complements for improvement. ( 0,516012253454592 )
J. Comput. Biol. - Determining protein structures from NOESY distance constraints by semidefinite programming. ( 0,515723041602445 )
IEEE Trans Pattern Anal Mach Intell - A Search-and-Validate Method for Face Identification from Single Line Drawings. ( 0,514871022619813 )
IEEE Trans Neural Netw Learn Syst - An Interval Type-2 Neural Fuzzy System for Online System Identification and Feature Elimination. ( 0,514715163672403 )
IEEE Trans Image Process - An alternating direction algorithm for total variation reconstruction of distributed parameters. ( 0,514602622965115 )
Neural Comput - Neural decoding with kernel-based metric learning. ( 0,513143799976087 )
Comput Math Methods Med - Analysis of a multilevel diagnosis decision support system and its implications: a case study. ( 0,512720119506185 )
IEEE Trans Image Process - Coupled dictionary training for image super-resolution. ( 0,511962305725677 )
IEEE Trans Image Process - Sparse stochastic processes and discretization of linear inverse problems. ( 0,510745698342746 )
Med Biol Eng Comput - Thalamic reticular cells firing modes and its dependency on the frequency and amplitude ranges of the current stimulus. ( 0,509875937944403 )
Comput Math Methods Med - Study on parameter optimization for support vector regression in solving the inverse ECG problem. ( 0,509418080850778 )
IEEE Trans Neural Netw Learn Syst - Comparison of l1-Norm SVR and Sparse Coding Algorithms for Linear Regression. ( 0,509052664647397 )
Neural Comput - A neural mass model with direct and indirect excitatory feedback loops: identification of bifurcations and temporal dynamics. ( 0,507683225783813 )
IEEE Trans Image Process - Approximate least trimmed sum of squares fitting and applications in image analysis. ( 0,50719599500418 )
IEEE Trans Image Process - Solving inverse problems with piecewise linear estimators: from Gaussian mixture models to structured sparsity. ( 0,506290059406811 )
IEEE Trans Image Process - Image segmentation using local variation and edge-weighted centroidal Voronoi tessellations. ( 0,506153142552485 )
IEEE Trans Pattern Anal Mach Intell - Optimized Product Quantization. ( 0,506070229318619 )
Neural Comput - Noninvertibility, chaotic coding, and chaotic multiplexity of synaptically modulated neural firing. ( 0,504283964154397 )
Comput Methods Programs Biomed - General bounds for electrode mislocation on the EEG inverse problem. ( 0,504270469552421 )
IEEE Trans Neural Netw Learn Syst - A two-layer recurrent neural network for nonsmooth convex optimization problems. ( 0,503806823392384 )
IEEE Trans Image Process - Efficient algorithms for robust recovery of images from compressed data. ( 0,503349287147595 )