Zsolt Kalmar, Csaba Szepesvári, András Lörincz  Home/Search
Context Related
| inf.elte.hu/~lorincz/Fi...modbase.ps.gz iserv.iki.kfki.hu/pub/p...modbase.ps.gz sneaker.mindmaker.kfkipar...ml98.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: inf.elte.hu/~lorincz/pub (more) From: iserv.iki.kfki.hu/New/pub (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: . The behavior of reinforcement learning (RL) algorithms is best understood in completely observable, discrete-time controlled Markov chains with finite state and action spaces. In contrast, robot-learning domains are inherently continuous both in time and space, and moreover are partially observable. Here we suggest a systematic approach to solve such problems in which the available qualitative and quantitative knowledge is used to reduce the complexity of learning task. The steps of the... (Update)
Context of citations to this paper: More
.... of low level actuator control was proposed by Mataric in its PhD thesis [15] and later on this approach was adopted by other authors [16, 17]. Dorigo and Colombetti combined RL and Classifier Systems to produce highly autonomous robots [18] based on a formalisation of the...
Cited by: More
Experiments in Robot Control for an Instance-Based.. - Ribeiro, Hemerly (1999) (Correct)
Similar documents (at the sentence level):
27.0%: Module Based Reinforcement Learning for a Real Robot - Kalm'ar (Correct)
Active bibliography (related documents): More All
0.8: Multi-criteria Reinforcement Learning - Gabor, Kalmar, Szepesvari (1998) (Correct)
0.7: Between MDPs and Semi-MDPs: A Framework for Temporal.. - Sutton, Precup, Singh (1999) (Correct)
0.5: A Unified Framework for Hybrid Control: Model and.. - Branicky, Borkar, Mitter (1998) (Correct)
Similar documents based on text: More All
1.1: Some Basic Facts Concerning Minimax Sequential Decision Processes - Szepesvari (1996) (Correct)
1.1: Certainty Equivalent Policies Are Self-Optimizing Under.. - Szepesvári (1996) (Correct)
1.0: Approximate Inverse-Dynamics Based Robust Control Using .. - Szepesvári.. (1997) (Correct)
BibTeX entry: (Update)
Z. Kalmar, C. Szepesvari, and A. Lorincz. Module-based reinforcement learning: Experiments with a real robot. Machine Learning. to appear. http://citeseer.ist.psu.edu/kalmar98modulebased.html More
@article{ kalmar97module,
author = {Zs. Kalmar and Cs. Szepesvari and A. Lorincz},
title = {Module-Based Reinforcement Learning: Experiments with a Real Robot},
journal = {Machine Learning},
year = "1997",
volume = "31",
number = {1--3},
pages = {55--85},
month = {April},
url = {citeseer.ist.psu.edu/kalmar98modulebased.html} }
Citations (may not include all citations):408 Princeton University Press (context) - Bellman - 1957
374 Reinforcement learning: A survey - Kaebling, Littman et al. - 1996
288 Planning in a hierarchy of abstraction spaces (context) - Sacerdoti - 1974
281 Machine Learning (context) - Watkins, Dayan - 1992
257 Learning to act using real-time dynamic programming - Barto, Bradtke et al. - 1995
255 Human Problem Solving (context) - Newell, Simon - 1972
183 Automatic programming of behavior-based robots using reinfor.. - Mahadevan, Connell - 1992
125 Learning to coordinate behaviors - Maes, Brooks - 1990
110 Generalization in reinforcement learning: Successful example.. - Sutton - 1996
107 the convergence of stochastic iterative dynamic programming .. - Jaakkola, Jordan et al. - 1994
94 Hybrid models for motion control systems (context) - Brockett - 1993
87 Reinforcement learning with hierarchies of machines - Parr, Russell - 1997
80 The role of exploration in learning control - Thrun - 1992
78 A qualitative physics based on confluences (context) - de Kleer, Seely - 1984
71 Asynchronous stochastic approximation and q-learning (context) - Tsitsiklis - 1994
70 Computational Mechanisms for Action Selection (context) - Tyrrell - 1993
66 Robot shaping: Developing autonomous agents through learning (context) - Dorigo, Colombetti - 1994
63 An analysis of temporal difference learning with function ap.. - Tsitsiklis, Van Roy - 1995
60 Purposive behavior acquisition for a real robot by vision-ba.. - Asada, Noda et al. - 1996
59 Feature-based methods for large scale dynamic programming - Tsitsiklis, Van Roy - 1996
55 volume 736 of Lecture Notes in Computer Science (context) - Grossman, Nerode et al. - 1993
51 Finding structure in reinforcement learning - Thrun, Schwartz - 1995
43 Reinforcement learning in the multi-robot domain (context) - Matari'c - 1997
35 Alecsys and the autonomouse: Learning to control a real robo.. - Dorigo - 1995
28 Complexity analysis of real-time reinforcement learning appl.. - Koenig, Simmons - 1997
27 Behavior coordination for a mobile robot using modular reinf.. - Uchibe, Asada et al. - 1996
23 How to dynamically merge markov decision processes - Singh, Cohn - 1997
21 Adaptive Behavior (context) - Wiering, Schmidhuber - 1997
15 Advanced forecasting methods for global crisis warning and m.. (context) - Werbos - 1977
13 Modeling agents as qualitative decision makers - Brafman, Moshe - 1997
11 A unified framework for hybrid control: Background (context) - Branicky, Borkar et al. - 1994
10 The loss from imperfect value functions in expectation-based.. (context) - Heger - 1996
6 Qualitative system identification: deriving structure from b.. (context) - Say, Selahattin - 1996
5 Module based reinforcement learning for a real robot (context) - Kalm'ar, Szepesv'ari et al. - 1997
4 Vector-valued dynamic programming (context) - Henig - 1983
3 Algorithms for design of hybrid systems (context) - Sastry - 1997
2 Research Group on Artificial Intelligence (context) - G'abor, Kalm'ar et al. - 1998
2 Optimal control by means of switching (context) - Zabczyk - 1973
2 Laboratory of Information and Decision (context) - Branicky, Hybrid et al. - 1995
2 Genetic algorithm with alphabet optimization - T'oth, Kov'acs et al. - 1995
1 Also Technical Report CS-96-09 (context) - Littman, Sequential et al. - 1996
1 Temporal Credit Assignment in Reinforcement Learning (context) - LEARNING, Sutton - 1984
1 Sixth European Workshop on Learning Robots (context) - Birk, Demiris - 1998
Documents on the same site (http://www.inf.elte.hu/~lorincz/pub.html): More
Output Sensitive Discretization for Genetic.. - Kovács.. (Correct)
Identification of Born-Oppenheimer potential energy surfaces of.. - Amstrup (Correct)
Towards A Unified Model Of Cortical Computation II: From Control.. - Lörincz (1997) (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