Valery Kuzmin  Home/Search
Context
Related
| dssg.cs.rtu.lv/en/...minRTU2002.ps.gz Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: dssg.cs.rtu.lv/en/publ...publ2002 (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: The study deals with the Q-learning algorithm that belongs to reinforcement learning algorithms. The use of neural networks in the Q-learning algorithm and in its modifications - the modified Q-learning and the Q(lambda) algorithm - is considered. Each algorithm is examined in the context of two methodologies enabling one to speed up the process of learning: backward replay and online learning. Efficiency analysis of the algorithms was performed experimentally by means of a software robot... (Update)
Active bibliography (related documents): More All
0.2: Function Approximation With Continuous-Valued.. - Martin Eldracher, .. (1994) (Correct)
0.2: Connectionist Adaptive Control - Jervis (1993) (Correct)
0.2: Reinforcement Learning on a Omnidirectional Mobile Robot - Hafner, Riedmiller (2003) (Correct)
Similar documents based on text: More All
0.5: Experiments in Robot Control for an Instance-Based.. - Ribeiro, Hemerly (1999) (Correct)
0.4: From Q(lambda) to Average Q-learning: Efficient Implementation .. - Garcia, Serre (Correct)
0.4: Integrating Experimentation and Guidance in Relational.. - Driessens, al. (2002) (Correct)
BibTeX entry: (Update)
@inproceedings{ kuzmin-connectionist,
author = "Valery Kuzmin",
title = "Connectionist Q-Learning In Robot Control Task" }
booktitle = "PScientific proceeding of Riga Technical University 5.serija. Datorzinatne. Information technology and management science, 10. sejums.",
address = "Riga, Latvia",
pages = "88--98",
year="2002",
url = "citeseer.ist.psu.edu/kuzmin02connectionist.html" }
Citations (may not include all citations):614 Reinforcement learning: an introduction - Sutton, Barto - 1998
563 Learning to predict by methods of temporal differences - Sutton - 1988
84 Neuron-like elements that can solve difficult learning contr.. (context) - Barto, Sutton et al. - 1983
65 Knowledge growth in an artificial animal (context) - Wilson - 1985
55 Incremental multi-step Q-learning - Peng, Williams - 1994
49 Q-Learning (context) - Watkins, Dayan - 1992
26 Memory approaches to reinforcement learning in nonMarkovian .. - Long-Ji - 1992
20 line Q-Learning using connectionist systems - Rummery, Niranjan - 1994
19 Automatic Programming of Behaviour-based Robots using Reinfo.. (context) - Mahadevan, Connelly - 1992
5 Reinforcement Learning for Multi-linked Manipulator Control (context) - Tham, Prager - 1992
1 Implementation details of TD(,) procedure for case of vector.. (context) - Sutton - 1989
Documents on the same site (http://dssg.cs.rtu.lv/en/publications/publ2002.html): More
ANGIE: Adaptive Network for Granular Information and.. - Valishevsky, Borisov (2002) (Correct)
The Digital Calculations Method Of The Neural Network - Kozlov (2002) (Correct)
Learning Classifier Systems in Autonomous Agent Control Tasks - Borisov, Vasilyev (2002) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC