Andrea Bonarini, Claudio Bonacina, Matteo Matteucci  Home/Search
Context
Related
| cmu.edu/~matteo/Download...IEEERFRL.ps 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: cmu.edu/~matteo/paper (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: The success of any reinforcement learning (RL) application is in large part due to the design of an appropriate reinforcement function. A methodological framework to support the design of reinforcement functions has not been de ned yet, and this critical and often underestimated activity is left to the ability of the RL application designer. We propose an approach to support reinforcement function design in RL applications concerning learning behaviors for autonomous agents. We de ne some... (Update)
Active bibliography (related documents): More All
1.2: Learning Fuzzy Classifier Systems: Architecture and Exploration.. - Matteucci (2000) (Correct)
1.2: Fuzzy and Crisp Representations - Of Real-Valued Input (Correct)
0.8: Fuzzy and Crisp Representations of Real-valued Input.. - Bonarini, Bonacina.. (2000) (Correct)
Similar documents based on text:
0.0: Unknown - (Correct)
BibTeX entry: (Update)
@misc{ bonarini-approach,
author = "Andrea Bonarini and Claudio Bonacina and Matteo Matteucci",
title = "An Approach to the Design of Reinforcement Functions in Real World, Agent-Based
Applications",
url = "citeseer.ist.psu.edu/751916.html" }
Citations (may not include all citations):614 Reinforcement Learning An Introduction - Sutton, Barto - 1999
374 Reinforcement learning: a survey - Kaelbling, Littman et al. - 1996
281 Machine Learning (context) - Watkins, Dayan - 1992
83 Reinforcement learning with replacing eligibility traces - Singh, Sutton - 1996
60 Learning to perceive and act by trial and error (context) - Whitehead, Ballard - 1991
39 Evolutionary learning of fuzzy rules: competition and cooper.. - Bonarini - 1996
38 Learning to predict by the method of temporal di erences (context) - Sutton - 1988
37 Robot shaping: an experiment in behavior engineering - Dorigo, Colombetti - 1997
32 converges with probability - Dayan, Sejnowski - 1994
16 Classi er tness based on accuracy (context) - Wilson - 1995
13 Classi er systems and genetic algorithms (context) - Booker, Goldberg et al. - 1989
12 The Role of the Trainer in Reinforcement Learning - Dorigo, Colombetti - 1994
10 Neural network fundamentals with graphs (context) - Bose, Liang - 1996
9 Reward functions for accelerated learning - Matari - 1994
8 and Adam Grove (context) - Bacchus, Boutilier - 1996
6 Comparing reinforcement learning algorithms applied to crisp.. (context) - Bonarini - 1999
5 Reinforcement distribution to fuzzy classi ers: a methodolog.. (context) - Bonarini - 1998
5 PID Controllers: Theory (context) - Astrom, Hagglund - 1995
5 Fuzzy and crisp representation of real-valued input for lear.. - Bonarini, Bonacina et al. - 1999
5 Fuzzy and crisp representation of real-valued input for lear.. - Bonarini, Bonacina - 2000
3 Purposive behaviour acquisition on a real robot by a vision .. (context) - Asada, Noda et al. - 1994
3 Contribution to the study and the design of reinforcement fu.. (context) - Santos - 1999
3 Anytime learning and adaptation of hierarchical fuzzy logic .. (context) - Bonarini - 1997
3 Reinforcement learning in the multi-robot domain (context) - Matari - 1997
3 Learning fuzzy classi er systems (context) - Bonarini - 2000
2 Learning Classi er System: From Foundation to Application (context) - Lanzi, Stolzmann et al. - 2000
1 Dynamic update of the reinforcement function during learning (context) - Santos, Touzet - 1999
1 Fuzzy learning classi er system: Issues and architecture (context) - Matteucci - 1999
1 Ecient exploration in reinforcement learning with hidden sta.. (context) - McCallum - 1997
Documents on the same site (http://www.cs.cmu.edu/~matteo/paper.html): More
Learning Fuzzy Classifier Systems: Architecture and Exploration.. - Matteucci (2000) (Correct)
Fuzzy and Crisp Representations - Of Real-Valued Input (Correct)
A Framework for Robust Sensing - In Multi Agent (2001) (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