ESANN 2008 - PDF Preprint Papers

ESANN 2008

Teaser Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed ESANN-2008 Paper

click to vote

ESANN
2008

278views Neural Networks» more ESANN 2008»

Learning to play Tetris applying reinforcement learning methods

14 years 1 months ago

Download www.dice.ucl.ac.be

In this paper the application of reinforcement learning to Tetris is investigated, particulary the idea of temporal difference learning is applied to estimate the state value funct...

Alexander Groß, Jan Friedland, Friedhelm Sch...

claim paper

Read More »

Disclaimer and Copyright Notice

Sciweavers respects the rights of all copyright holders and in this regard, authors are only allowed to share a link to their preprint paper on their own website. Every contribution is associated with a desciptive image. It is the sole responsibility of the authors to ensure that their posted image is not copyright infringing. This service is compliant with IEEE copyright.

Id	Views	Title	Status

1	278	Learning to play Tetris applying reinforcement learning methods	claim
2	210	Petri nets design based on neural networks	claim
3	205	An accelerated MDM algorithm for SVM training	claim
4	189	Approximation of Gaussian process regression models after training	claim
5	188	SOM based clustering with instance-level constraints	claim
6	188	An emphasized target smoothing procedure to improve MLP classifiers performance	claim
7	174	A Regularized Learning Method for Neural Networks Based on Sensitivity Analysis	claim
8	164	Multilayer Perceptrons with Radial Basis Functions as Value Functions in Reinforcement Learning	claim
9	163	Clustering of Self-Organizing Map	claim
10	158	Learning Data Representations with Sparse Coding Neural Gas	claim
11	153	An automatic identifier of Confinement Regimes at JET combining Fuzzy Logic and Classification Trees	claim
12	150	Conditional prediction of time series using spiral recurrent neural network	claim
13	149	Detecting zebra crossings utilizing AdaBoost	claim
14	149	Robust object segmentation by adaptive metrics in Generalized LVQ	claim
15	149	A method for robust variable selection with significance assessment	claim
16	143	Consistency of Derivative Based Functional Classifiers on Sampled Data	claim
17	143	An FPGA-based model suitable for evolution and development of spiking neural networks	claim
18	143	Computational model for amygdala neural networks	claim
19	142	Interpretable ensembles of local models for safety-related applications	claim
20	142	Simulation of a recurrent neurointerface with sparse electrical connections	claim
21	139	A Methodology for Building Regression Models using Extreme Learning Machine: OP-ELM	claim
22	139	Multi-class classification of ovarian tumors	claim
23	138	Active and reactive use of virtual neural sensors	claim
24	137	Classification of chestnuts with feature selection by noise resilient classifiers	claim
25	136	Generalized matrix learning vector quantizer for the analysis of spectral data	claim
26	135	Learning Inverse Dynamics: a Comparison	claim
27	133	Linear Projection based on Noise Variance Estimation - Application to Spectral Data	claim
28	131	Parallelizing single patch pass clustering	claim
29	129	Pruning and Regularisation in Reservoir Computing: a First Insight	claim
30	128	A Method for Time Series Prediction using a Combination of Linear Models	claim
31	127	Using graph-theoretic measures to predict the performance of associative memory models	claim
32	127	Neural networks for computational neuroscience	claim
33	126	Improving a statistical language model by modulating the effects of context words	claim
34	125	Improvement in Game Agent Control Using State-Action Value Scaling	claim
35	125	Automatic alignment of medical vs. general terminologies	claim
36	125	Parallel asynchronous neighborhood mechanism for WTM Kohonen network implemented in CMOS technology	claim
37	125	Methodology and standards for data analysis with machine learning tools	claim
38	124	Explaining Ant-Based Clustering on the basis of Self-Organizing Maps	claim
39	123	Safe exploration for reinforcement learning	claim
40	122	GeoKernels: modeling of spatial data on geomanifolds	claim
41	121	A neural model with feedback for robust disambiguation of motion	claim
42	118	Using the Delta Test for Variable Selection	claim
43	118	Word recognition and incremental learning based on neural associative memories and hidden Markov models	claim
44	117	Machine learning in cancer research: implications for personalised medicine	claim
45	117	Computationally Efficient Neural Field Dynamics	claim
46	117	Inverting hyperspectral images with Gaussian Regularized Sliced Inverse Regression	claim
47	116	Rank-based quality assessment of nonlinear dimensionality reduction	claim
48	115	Similarities and differences between policy gradient methods and evolution strategies	claim
49	115	Survival SVM: a practical scalable algorithm	claim
50	113	Do we need experts for time series forecasting?	claim
51	113	Discrimination of regulatory DNA by SVM on the basis of over- and under-represented motifs	claim
52	112	Visual focus with spiking neurons	claim
53	112	Homogeneous bipartition based on multidimensional ranking	claim
54	112	K-nearest neighbours based on mutual information for incomplete data classification	claim
55	111	Self-Organizing Maps for cyclic and unbounded graphs	claim
56	111	Metric adaptation for supervised attribute rating	claim
57	111	Feature Selection in Proton Magnetic Resonance Spectroscopy for Brain Tumor Classification	claim
58	110	A multiple testing procedure for input variable selection in neural networks	claim
59	110	Factored sequence kernels	claim
60	110	Direct and inverse solution for a stimulus adaptation problem using SVR	claim
61	108	Neural network hardware architecture for pattern recognition in the HESS2 project	claim
62	107	A novel autoassociative memory on the complex hypercubic lattice	claim
63	107	On related violating pairs for working set selection in SMO algorithms	claim
64	107	The gamma cycle and its role in the formation of assemblies	claim
65	104	The impact of axon wiring costs on small neuronal networks	claim
66	103	Selection of important input variables for RBF network using partial derivatives	claim
67	100	Emergence of stimulus-specific synchronous response through STDP in recurrent neural networks	claim
68	100	Initialization mechanism in Kohonen neural network implemented in CMOS technology	claim
69	96	Model-Based Reinforcement Learning with Continuous States and Actions	claim
70	91	Phase transitions in Vector Quantization	claim
71	91	Neuromimetic motion indicator for visual perception	claim
72	90	Comparison of sparse least squares support vector regressors trained in primal and dual	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers