http:^^envy.cs.umass.edu^people^barto^barto.html

来自「This data set contains WWW-pages collect」· HTML 代码 · 共 484 行 · 第 1/2 页

robotics,&quot <i>Proceedings of the Ninth International Joint Conference in
Artificial Intelligence</i>. 1985, San Mateo, CA: Morgan Kaufmann, pp. 670-672.
<P>
A.G. Barto and C.W. Anderson, ``Structural Learning in Connectionist
Systems, &quot <i>Proceedings of the Seventh Annual Conference of the Cognitive
Science Society</i>. Irvine, CA, August 1985, pp. 43-54.
<P>
A.G. Barto and P. Anandan, ``Pattern recognizing stochastic learning automata,&quot;
<i>IEEE Trans. on Systems, Man, and Cybernetics</i>, <b>15</b>: 360-375, 1985.
<P>
A.G. Barto, R.S. Sutton and C.W. Anderson, ``Neuron-like adaptive elements that
can solve difficult learning control problems,&quot 
<i>IEEE Trans. on Systems, Man, and Cybernetics</i>, <b>SMC-13</b>: 834-846,
1983. (Reprinted in <i>Neurocomputing: Foundations of Research</i>,
J.A. Anderson and E. Rosenfeld (Eds.), Cambridge, MA: The MIT Press, 1988,
pp. 537-549.)
<P>
A.G. Barto, R.S. Sutton and C.W. Anderson, ``Spatial learning 
simulation systems,&quot
 <i>Proceedings of the 10th IMACS World
Congress on Systems Simulation and Scientific Computation</i>, 1982, pp. 204-206.
<P>
A.G. Barto,  C.W. Anderson and R.S. Sutton, ``Synthesis of nonlinear control surfaces by a layered
associative network,&quot; <i>Biological Cybernetics</i>, <b>43</b>:
175-185, 1982.
<P>
A.G. Barto and R.S. Sutton,  ``Simulation of anticipatory responses in classical
conditioning by a neuron-like adaptive element,&quot 
<i>Behavioural Brain Research</i>, <b>4</b>: 221-235, 1982.
<P>
A.G. Barto and R.S. Sutton, ``An adaptive network that constructs and uses an
internal model of its environment,&quot  <i>Cognition and Brain
Theory</i>, <b>4</b>:  217-246, 1981.
<P>
A.G. Barto and R.S. Sutton, ``Landmark learning: An illustration of associative
search,&quot  <i>Biological Cybernetics</i>, <b>42</b>: 1-8, 1981.
<P>
A.G. Barto,  R.S. Sutton and P. Brouwer, ``Associative search network: A
reinforcement learning associative memory,&quot  <i>Biological Cybernetics</i>,
<b>40</b>: 201-211, 1981.
<P>
R.S. Sutton and A.G. Barto, ``Toward a modern theory of adaptive networks:
Expectation and prediction,&quot  <i>Psychological Review</i>, <b>88</b>:
135-170, 1981. 
<P>
A.G. Barto, ``Invariant linear models of varying linear systems,&quot <i>NATO
Conference Series, Series II, Systems Science</i>, <b>5</b>, G. Klir (Ed.),
Plenum, New York, 1978.
<P>
A.G. Barto, ``A note on pattern reproduction in tesselation structures,&quot; <i>Journal
of Computer and Systems Sciences</i>, <b>16</b>: 445-455, 1978.
<P>
A.G. Barto, ``Discrete and continuous models,&quot <i>International Journal of
General Systems</i>, <b>4</b>: 163-177, 1978.
<P>
A.G. Barto, ``A neural network simulation method using the Fast Fourier
 Transform,&quot
<i>IEEE Transactions on Systems, Man, and Cybernetics</i>, <b>SMC-5</b>:
863-867, 1976.
<hr>
<H3><A NAME = "Chapters">Book Chapters</A></H3>
<P>
A. G. Barto.  ``Learning as hillclimbing in weight space.&quot  In <i>Handbook
of Brain Theory and Neural Networks,</i> M.A. Arbib (Ed.), Cambridge: MIT Press,
1995.
<P>
A. G. Barto.  ``Reinforcement learning in motor control.&quot  In <i>Handbook 
of Brain Theory and Neural Networks,</i> M.A. Arbib (Ed.), Cambridge: MIT Press,
1995.
<P>
A. G. Barto.  ``Reinforcement learning.&quot  In <i>Handbook of Brain Theory
and Neural Networks,</i> M.A. Arbib (Ed.), Cambridge: MIT Press, 1995.
<P>
J. C. Houk, J. L. Adams, and A. G. Barto.  ``A model of how the basal ganglia
generates and uses neural signals that predict reinforcement.&quot  <i>Models
of Information Processing in the Basal Ganglia,</i> J. C. Houk, J. 
Davis and D. Beiser (Eds.), Cambridge, MA: MIT Press, 1995, pp. 249-270.
<P>
A. G. Barto.  ``Adaptive critics and the basal ganglia.&quot  In <i>Models of
Information Processing in the Basal Ganglia,</i> J. C. Houk, J. 
Davis and D. Beiser (Eds.), Cambridge, MA: MIT Press, 1995, pp. 215-232.
<P>
A. G. Barto and V. Gullapalli.  ``Neural networks and adaptive control.&quot
In  P. Rudomin, M.A. Arbib and F. Cervantes-Perez, and R. Romo, editors, <i>Neuroscience:  From Neural Networks to  Artificial Intelligence,</i> Research
Notes in Neural Computation, Vol. 4, Springer-Verlag, 1993, pp. 471-493.
<P>
A. G. Barto, ``Reinforcement Learning and Adaptive Critic Methods.&quot In
<i>Handbook of
Intelligent Control: Neural, Fuzzy, and Adaptive Approaches</i>.
D. A. White and D. A. Sofge (Eds.). New York: Van Nostrand Reinhold
1992, pp. 469-491.
<P>
A.G. Barto.  ``Learning algorithms.&quot In <i>Encyclopedia of Learning and
Memory</i>.  L.R. Squire (Ed.).  New York: MacMillan, 1992.
<P>
A.G. Barto.  ``Reinforcement learning and adaptive critic methods.&quot In
<i>Handbook of Intelligent Control.</i> D.A. white and D.A. Sofgee (Eds.), New
York: Van Nostrand Reinhold, 1992, pp. 469-491.
<P>
J.C. Houk and A.G. Barto. ``Distributed sensorimotor learning.&quot In
<i>Tutorials in Motor Behavior II</i>. G.E. Stelmach and J. Requin (Eds.).
Amsterdam: Elsevier Science Publishers,  1992, pp. 71-100. 
<P>
A.G. Barto, ``Some learning problems from the perspective of control.&quot In
<i>1990 Lectures in  Complex Systems.</i>
L. Nadel and D.L. Stein (Eds.). Redwood
City: Addison-Wesley, 1991, pp. 195-223. 
<P>
A.G. Barto and S.P. Singh, ``On the computational economics of reinforcement
learning.&quot In <i>Proceedings of the 1990 Connectionist Models Summer
School</i>. D.S. Touretzky, J.L. Elman, T.J. Sejnowski, and G.E. Hinton (Eds.).
San Mateo, CA: Morgan Kaufmann, 1990, pp. 35-44.
<P>
J.C. Houk, S.P. Singh,  C. Fisher and A.G. Barto, 
``An adaptive network inspired by the anatomy and physiology of the 
cerebellum.&quot In <i>Neural Networks for
Control</i>.  T. Miller, R.S. Sutton, and P.J. Werbos (Eds.), Cambridge, MA: MIT
Press, 1990, pp. 301-348.
<P>
A.G. Barto, ``Connectionist learning for control: An overview.&quot In <i>Neural
Networks for Control</i>.  T. Miller, R.S. Sutton, and P.J. Werbos (Eds.),
Cambridge, MA: MIT Press, 1990, pp. 5-58.
<P>
R.S. Sutton and A.G. Barto, ``A time-derivative theory of 
Pavlovian conditioning.&quot
In <i>Learning and Computational Neuroscience</i>.
M. Gabriel and J.W. Moore (Eds.), Cambridge, MA: MIT Press, 1990, pp. 497-537.
<P>
A.G. Barto, R.S. Sutton and C. Watkins, ``Learning and sequential decision 
making.&quot  In <i>Learning and Computational Neuroscience</i>.
M. Gabriel and J.W. Moore (Eds.), Cambridge, MA: MIT Press, 1990, pp. 539-602.
<P>
A.G. Barto, ``From chemotaxis to cooperativity: Abstract exercises in
neuronal learning strategies.&quot In <i>The Computing Neuron</i>.
R. Durbin, R. Maill, and G. Mitchison (Eds.), Reading, MA: Addison-Wesley,
1989, pp. 73-98.
<P>
A.G. Barto, ``An approach to learning control surfaces by connectionist
systems.&quot In <i>Vision, Brain and Cooperative Computation</i>.
M.A. Arbib and A.R. Hanson (Eds.), Cambridge, MA:
MIT Press, 1987, pp. 665-701.
<P>
A.G. Barto and  R.S. Sutton, ``Neural problem solving.&quot In <i>Synaptic 
Modification, Neuron Selectivity, and Nervous System Organization</i>.
W. B. Levi, J. A. Anderson and S. Lehmkuhle (Eds.),
Hillsdale, NJ: Erlbaum, 1983, pp. 123-152.
<hr>

<H3><A NAME = "Other">Other Publications</A></H3>
<P>
J. T. Buckingham, A. G. Barto, and J. C. Houk.  ``Adaptive Predictive
Control with a Cerebellar Model.&quot In <i>Proceedings of the 1995 World
Congress on Neural Networks, Volume 1</i>,  Lawrence Erlbaum
Associates, Inc: Mahwah, NJ, 1995,  pp. 373-380.
<p>
A. G. Barto. `` Reinforcement learning and dynamic programming.&quot
<i>Proceedings of the 6th IFAC/IFIP/IFORS/IEA Symposium on Analysis, Design,
and Evaluation of Man-Machine Systems.</i>
Cambridge, MA, June 1995. pp. 469-474.
<P>
A. G. Barto.  ``Reinforcement learning control.&quot  <i>Current Opinion in
Neurobiology,</i> <b>4</b>: 888-893, December 1994.
<P>
A. G. Barto. Forward for <i>Adaptive, Learning and Pattern Recogintion Systems: Theory and
Applications,</i> Second Edition. J. M. Mendel and K. S. Fu (Eds.). To appear.
<P>
R.S. Sutton, A.G. Barto, and R.J. Williams. ``Reinforcement Learning is Direct
Adaptive Optimal Control.&quot <i>Proceedings of the 1991 American Control
Conference</i>. American Automatic Control Council, 1991, pp. 2143-2146.
<P>
A.G. Barto, ``Learning and Incremental Dynamic Programming.&quot
Commentary on C. W. Clark's ``Modeling Behavioral Adaptations,&quot
<i>Behavioral Brain Science</i>, Vol. 14, 1991, pp. 94-95.
<P>
N.E. Berthier, A.G. Barto, and J.C. Houk. ``A Network Model of the Cerebellum
that Uses a Trained Set of Pattern Generators to Control a Single
Degree-of-Freedom Joint.&quot <i>Society for Neuroscience Abstracts</i>. 
Vol. 17, p. 1382, 1991.
<P>
A.G. Barto, N.E. Berthier, S.P. Singh, and J.C. Houk,
``Network model of the cerebellum and motor cortex that learns to control
planar limb movements.&quot  Abstract,
<i>Society of Neuroscience Abstracts</i>, Vol. 16, Part 2, p. 1223, 1990.
<P>
V. Srinivasan, A.G. Barto and B.E. Ydstie, 
``Pattern recognition and feedback via parallel distributed
processing.&quot  Abstract,
Annual Meeting of the AIChE, Washington DC, November, 1988.
<P>
A.G. Barto (editor), ``Multilayer networks of self-interested adaptive
units.&quot  Final Technical Report AFWAL-TR-87-1052, Avionics
Laboratory (AFWAL/AAAT), Air Force Wright Aeronautical Laboratories,
Wright-Patterson Air Force Base, OH 45433, 1987.
<P>
A.G. Barto, ``Adaptive neural networks for learning control: Some
computational experiments.&quot <i>Proceedings of the IEEE Workshop on
Intelligent Control</i>, Rensselaer Polytechnic Institute, Troy, NY, August 1985.
<P>
A.G. Barto,  P. Anandan and C.W. Anderson, ``Cooperativity in networks of
pattern recognizing stochastic learning automata.&quot <i>Proceedings
of the Fourth Yale Workshop on Applications of Adaptive Systems Theory</i>,
New Haven, CT, May 1985 (an extended version appears in
<i>Adaptive and Learning Systems</i>, K.S. Narendra (Ed.),
New York: Plenum Press, 1986, pp. 235-246).
<P>
A.G. Barto (editor), ``Simulation experiments with goal-seeking adaptive
elements.&quot  Final Technical Report AFWAL-TR-84-1022, Avionics
Laboratory (AFWAL/AAAT), Air Force Wright Aeronautical Laboratories,
Wright-Patterson Air Force Base, Ohio 45433, 1984.
<P>
A.G. Barto, Review of S. Grossberg's <i>Studies of Mind and Brain</i>, <i>Mathematical
Biosciences,</i> <b>70</b>, New York: D. Reidel Publishing Company,
1982, pp. 111-113.
<P>
A.G. Barto and S. Epstein, ``Adaptive networks and sensorimotor control.&quot 
 <i>Proceedings of the Second Workshop on Visuomotor
Coordination in Frog and
Toad: Theory and Experiment</i>, November 1982, Mexico City, Mexico.
<P>
A.G. Barto and R.S. Sutton, ``Goal seeking components for adaptive 
intelligence: An initial assessment.&quot  Final Technical Report
AFWAL-TR-81-1070, Avionics Laboratory (AFWAL/AAAT), Air Force Wright
Aeronautical Laboratories, Wright-Patterson Air Force Base, Ohio 45433, 1981.
<P>
B.P. Zeigler and A.G. Barto, ``Alternative formalisms for biosystem and 
ecosystem modelling.&quot  In <i>New Directions in the Analysis of Ecological
Systems, Part 2</i>, G. Innis (Ed.), Simulation Councils Proceedings Series, 5, 
1977, pp. 167-178.
<P>
A.G. Barto, ``Cellular automata as models of natural systems.&quot Ph.D. Thesis,
Logic of Computers Group Technical Report, University of Michigan, 1975.
<P>
A.G. Barto, ``Simulation of networks using multidimensional Fast Fourier
Transforms.&quot <i>ACM Simuletter</i>, <b>5</b>, July 1974.


<hr>
<P><ADDRESS>
<I>[e-mail] <BR>
Fri Sep  8 13:57:14 EDT 1995</I>
</ADDRESS>