Maja J Mataric  Home/Search
Context Related
Links: ACM | mit.edu/aipublications/1...AIM1322.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: mit.edu/publications/pubsD...pubs (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: This paper analyzes the suitability of reinforcement learning for both programming and adapting situated agents. In the the first part of the paper we discuss two specific reinforcement learning algorithms: Q-learning and the Bucket Brigade. We introduce a special case of the Bucket Brigade, and analyze and compare its performance to Qlearning in a number of experiments. The second part of the paper discusses the key problems of reinforcement learning: time and space complexity, input... (Update)
Context of citations to this paper: More
.... they can use little domain knowledge, and hence like all weak learning algorithms are doomed to scale poorly to complex tasks (e.g. Mataric [72]) 2 Within theoretical computer science, the term DP is applied to a general class of methods for efficiently solving recursive...
...can be tried at every states. Figure 1(b) defines the state transitions as a function of present state and action. Previously, Mataric [7] has used this same world to study and compare the performance of Q learning and Bucket Brigade algorithms. In this domain, the task of...
Cited by: More
On Amount and Quality of Bias in Reinforcement Learning - Hailu, Sommer (Correct)
A Learning Classifier Systems Bibliography - Kovacs, Lanzi (1999) (Correct)
Learning To Solve Markovian Decision Processes - Singh (1994) (Correct)
Active bibliography (related documents): More All
0.1: Artificial Embryology - The Genetic Programming of Cellular.. - de Garis (1992) (Correct)
0.1: Differentiable Chromosomes - The Genetic Programming of.. - de Garis, Iba, Furuya (1992) (Correct)
0.1: Artificial Embryology - The Genetic Programming of an Artificial .. - de Garis (1992) (Correct)
Similar documents based on text: More All
0.5: Faster Temporal Credit Assignment in Learning Classifier Systems - Cichosz, Mulawka (Correct)
0.4: Evolution of a Clustering Scheme for a Classifier System: Beyond.. - Tufts (1994) (Correct)
0.3: Connectionist Q-Learning in Robot Control Task - Kuzmin (2002) (Correct)
Related documents from co-citation: More All
3: Knowledge growth in an articial animal (context) - Wilson - 1985
2: A mathematical framework for studying learning in classifier systems (context) - Holland - 1986
2: Incremental robot shaping (context) - Urzelai, Floreano et al. - 1998
BibTeX entry: (Update)
M.J. Mataric. A comparative analysis of reinforcement learning methods. Technical report, M.I.T., 1991. A.I. Memo No.1322. http://citeseer.ist.psu.edu/mataric91comparative.html More
@techreport{ mataric91comparative,
author = "Maja Mataric",
title = "A Comparative Analysis of Reinforcement Learning Methods",
number = "AIM-1322",
pages = "13",
year = "1991",
url = "citeseer.ist.psu.edu/mataric91comparative.html" }
Citations (may not include all citations):13 Bucket Brigade Performance (context) - Brigade, Se et al.
8 and machine learning (context) - in, optimization - 1989
1 David Chapman and Leslie P (context) - in, Learning et al.
1 Gerald Dejong and Raymond Mooney (context) - Learning, View - 1988
1 Watson Research Center Research Report (context) - of, using et al. - 1990
1 Machine earning: An Artificial Intelligence Approach (context) - brittleness, of et al. - 1986
1 CMU-CS-8-lOtl (context) - Robot, Mitchell et al. - 1989
1 Stanford Universitel (context) - Embedded, Leslie et al. - 1990
1 Keller and Smadar T (context) - Generalization, View et al. - 1986
1 Ohio State Universitel AI Lab TR O-JKBPSIC (context) - is, to et al. - 1990
1 IBM Journal of Research and Development (context) - in, using et al. - 1959
1 Sridhar Mahadevan and Jonathan Cormell (context) - ming, Robots et al. - 1991
1 The Journal of Machine earning (context) - predict, of et al. - 1988
1 King's College PhD Thesis (context) - Delayed, Watkins - 1989
1 Genetic algorithms and 11 simulated annealing (context) - allocation, system et al. - 1987
1 gnd edition (context) - Intelligence, Winston - 1984
Documents on the same site (http://www.ai.mit.edu/publications/pubsDB/pubs.html): More
Corpus-based Techniques for Word Sense Disambiguation - Levow (1997) (Correct)
Presentation Based User Interfaces - Ciccarelli (1984) (Correct)
The Revised Revised Report on Scheme or An UnCommon Lisp - Abelson, Adams, Bartley, .. (1985) (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