ALL Publications, 1978-1993

Please contact the lab or a specific author if you have any questions. To obtain copies of specific papers, please send email to mitchell [at] cs [dot] umass [dot] edu


1993

  • A. G. Barto and V. Gullapalli
    Neural networks and adaptive control
    Neuroscience: From Neural Networks to Artificial Intelligence, p. 471-493, Research Notes in Neural Computation, Vol. 4, Springer-Verlag, 1993.
    [pdf]
  • V. Gullapalli
    Robust control under extreme uncertainty
    Advances in Neural Information Processing Systems 5, p.327-334, 1993.
  • N. E. Berthier, S. P. Singh, A. G. Barto, and J. C. Houk
    Distributed representation of limb motor programs in arrays of adjustable pattern generators
    Journal of Cognitive Neuroscience, 5 (1): 56-78, 1993.
    [pdf]
  • S. J. Bradtke
    Reinforcement Methods Applied to Linear Quadratic Regulation
    Advances in Neural Information Processing Systems 5, p. 295-302, 1993.
  • S. Guzmán-Lara
    Adjusting connections using reflexes as guidance
    Technical Report 8. Center for the Study of Neuronal Populations and Behavior. August 1993.
  • J. C. Houk, J. Kiefer, and A. G. Barto
    Distributed motor commands in the limb premotor network
    Trends in Neuroscience, 16(1): 27-33, 1993.
    [pdf]
  • S. P. Singh
    Learning to Solve Markovian Decision Processes
    (Ph.D. Thesis) CMPSCI Technical Report 93-77, University of Massachusetts, November 1993.

1992

  • J. C. Houk and A. G. Barto
    Distributed sensorimotor learning
    Tutorials in Motor Behavior II, Elsevier Science Publishers B.V.: Amsterdam, 1992, pp. 71-100.
  • V. Gullapalli, R. A. Grupen and A. G. Barto
    Learning reactive admittance control
    Proceedings of the 1992 IEEE Conference on Robotics and Automation, p. 1475-1480, Nice, France, May 1992
    [pdf]
  • R. S. Sutton, A. G. Barto and R. J. Williams
    Reinforcement learning is direct adaptive optimal control
    Control Systems, IEEE 12.2: p. 19-22, 1992.
    [pdf]
  • J. W. Moore
    A mechanism for timing conditioned responses
    Technical Report 92-3, Computer Science Dept., University of Massachusetts, January 1992.
  • S.P. Singh
    Transfer of learning by composing solutions for elemental sequential tasks
    Machine Learning, 8: 323-339, May 1992.
  • N.E. Berthier, S.P. Singh, A.G. Barto and J.C. Houk
    A cortico-cerebellar model that learns to generate distributed motor commands to control a kinematic arm
    Neural Information Processing Systems 4, p. 611-618, 1992.
  • V. Gullapalli and A. G. Barto
    Shaping as a method for accelerating reinforcement learning
    Proceedings of the 1992 IEEE International Symposium on Intelligent Control, Glasgow, Scotland, August 1992.
    [pdf]
  • S. P. Singh
    Scaling reinforcement learning algorithms by learning variable temporal resolution models
    Proceedings of the Ninth Machine Learning Conference, p. 406-415, Aberdeen, Scotland, 1992.
  • J. R. Bachrach
    Connectionist Modeling and Control of Finite State Environments
    (Ph.D. Thesis) COINS Technical Report 92-6, University of Massachusetts, Amherst. January 1992.
  • V. Gullapalli
    Reinforcement Learning and its Application to Control
    (Ph.D. Thesis) COINS Technical Report 92-10, University of Massachusetts, Amherst. January 1992.
  • S. P. Singh
    Reinforcement learning with a hierarchy of abstract models
    Proceedings of the Tenth National Conference on Artificial Intelligence (AAAI-92), p. 202-207, San Jose, CA, July 1992.
  • S. P. Singh
    The efficient learning of multiple task sequences
    Advances in Neural Information Processing Systems 4, p. 251-258, 1992.
  • V. Gullapalli
    Dynamic systems control via associative reinforcement learning
    Dynamic, Genetic, and Chaotic Programming: The Sixth Generation, p. 27-64, 1992.
  • R. Yee
    Abstraction in control learning
    COINS Technical Report 92-16, University of Massachusetts, March 1992.
  • A. G. Barto
    Reinforcement learning and adaptive critic methods
    Handbook of Intelligent Control, New York: Van Nostrand Reinhold, p. 469-491, 1992.
  • A. G. Barto and S. J. Bradtke
    Learning to solve stochastic optimal path problems using real-time dynamic programming
    Proceedings of the Seventh Yale Workshop on Adaptive and Learning Systems, p. 143-148, New Haven, CT, May 1992.

1991

  • R. A. Jacobs, M. I. Jordan and A. G. Barto
    Task decomposition through competition in a modular connectionist architecture: The what and where vision tasks
    Cognitive Science, 15:219-250, 1991.
    [pdf]
  • M. C. Mozer and J. Bachrach
    SLUG: A connectionist architecture for inferring the structure of finite-state environments
    Machine Learning, 7(2/3): 139-160, 1991.
  • J.R. Bachrach
    A connectionist learning control architecture for navigation
    Advances in Neural Information Processing 3, p. 457-463, 1991.
  • A.G. Barto
    Some learning tasks from a control perspective
    1990 Lectures in Complex Systems, Addison-Wesley, 1991.
    [pdf]
  • S.P. Singh
    Transfer of learning across compositions of sequential tasks
    Machine Learning: Proceedings of the Eighth International Workshop, p. 348-352, 1991.
  • V. Gullapalli
    A comparison of supervised and reinforcement learning methods on a reinforcement learning task
    Proceedings of the 1991 IEEE International Symposium on Intelligent Control, p. 394-399, Arlington, VA, August 1991.
  • V. Gullapalli
    Associative reinforcement learning of real-valued functions
    Proceedings of the 1991 IEEE International Conference on Systems, Man, and Cybernetics, Charlottesville, VA, October 1991.

1990

  • A. G. Barto
    Connectionist learning for control
    In W. T. Miller, R. S. Sutton and P. J. Werbos,editors, Neural Networks for Control, pp. 5-58, Cambridge, MA: The MIT Press, 1990.
    [pdf]
  • A. G. Barto and S. P. Singh
    Reinforcement learning and dynamic programming
    Proceedings of the Sixth Yale Workshop on Adaptive and Learning Systems, New Haven, CT, August 1990. pp. 83-88.
  • A. G. Barto and S. P. Singh
    On the computational economics of reinforcement learning
    In D.S. Touretzky, J.L. Elman, T.J. Sejnowski and G.E. Hinton, editors, Proceedings of the 1990 Connectionist Models Summer School, pp. 35-44, 1990.
    [pdf]
  • A. G. Barto, R. S. Sutton and C. J. C. H. Watkins
    Learning and sequential decision making
    In M. Gabriel and J. Moore, editors, Learning and Computational Neuroscience, The MIT Press, Cambridge, MA, 1990, pp. 539-602.
    [pdf]
  • A. G. Barto, R. S. Sutton and C. J. C. H. Watkins
    Sequential decision problems and neural networks
    Advances in Neural Information Processing Systems 2, p. 686-693, San Mateo, CA, 1990.
    [pdf]
  • V. Gullapalli
    Associative reinforcement learning of real-valued functions
    COINS Technical Report 90-129, University of Massachusetts, May 1990.
  • V. Gullapalli
    Modeling cortical area 7a using stochastic real-valued (SRV) units
    Proceedings of the 1990 Connectionist Models Summer School, p. 363-368. San Mateo, CA, 1990.
  • V. Gullapalli
    A stochastic reinforcement learning algorithm for learning real-valued functions
    Neural Networks, 3:671-692, 1990.
  • J. C. Houk, S. P. Singh, C. Fisher and A. G. Barto
    An adaptive sensorimotor network inspired by the anatomy and physiology of the cerebellum
    Neural Networks for Control, p. 301-348. Cambridge, MA: MIT Press, 1990.
  • J. C. Houk
    Cooperative control of limb movements by the motor cortex, brainstem and cerebellum
    Models of Brain Function, Cambridge University Press, 1990.
  • R. A. Jacobs
    Task Decomposition Through Competition in a Modular Connectionist Architecture
    (Ph.D. Thesis) COINS Technical Report 90-44, University of Massachusetts at Amherst, May 1990.
  • M. I. Jordan and R. A. Jacobs
    Learning to control an unstable system with forward modeling
    Advances in Neural Information Processing Systems 2, p. 324-331, 1990.
  • M. C. Mozer and J. Bachrach
    Discovering the structure of a reactive environment by exploration
    Advances in Neural Information Processing Systems 2, p. 439-446, 1990.
  • M. C. Mozer and J. R. Bachrach
    Discovering the structure of a reactive environment by exploration
    Neural Computation, 2: 447-457, 1990.
  • R. S. Sutton and A. G. Barto
    Time-derivative models of Pavlovian reinforcement
    Learning and Computational Neuroscience, p. 497-537, The MIT Press: Cambridge, MA, 1990.
    [pdf]
  • B. E. Ydstie
    Forecasting and control using adaptive connectionist networks
    Computers in Chemical Engineering, 14: 583-299, 1990.
  • R. C. Yee, S. Saxena, P. E. Utgoff and A. G. Barto
    Explaining temporal differences to create useful concepts for evaluating states
    Proceedings of the 8th National Conference on Artificial Intelligence, p. 882-888, AAAI Press/MIT Press, 1990.
    [pdf]

1989

  • A. Barto
    From chemotaxis to cooperativity: Abstract exercises in neuronal learning strategies
    In R. Durbin, C. Miall and G. Mitchison, editors, The Computing Neuron, pp. 73-98, Wokingham, England: Addison-Wesley, 1989.
    [pdf]

1988

  • J. E. Desmond
    Temporally adaptive conditioned responses: Representation of the stimulus trace in neural-network models
    COINS Technical Report 88-80, University of Massachusetts, 1988.
  • V. Gullapalli
    A stochastic algorithm for learning real-valued functions via reinforcement feedback
    COINS Technical Report 88-91, University of Massachusetts, 1988.
  • R. A. Jacobs
    Increased rates of convergence through learning rate adaptation
    Neural Networks, 1:295-307, 1988.
  • R. A. Jacobs
    Initial experiments on constructing domains of expertise and hierarchies in connectionist systems
    Proceedings of the 1988 Connectionist Model Summer School, San Mateo, CA: Morgan Kaufmann, 1988.
  • M. I. Jordan
    Supervised learning and systems with excess degrees of freedom
    COINS Technical Report 88-27, University of Massachusetts.
  • M. I. Jordan and D. A. Rosenbaum
    Action
    Handbook of Cognitive Science,Cambridge, MA: MIT Press, 1988.
  • S. Judd
    On the complexity of loading shallow neural networks
    Journal of Complexity,1988.
  • R. S. Sutton
    Learning to predict by the methods of temporal differences
    Machine Learning,3: 9-44, 1988.

1987

  • A. G. Barto
    An approach to learning control surfaces by connectionist systems
    Vision, Brain and Cooperative Computation, MIT Press/Bradford Books, Cambridge, MA, 1987.
  • A. G. Barto and M. I. Jordan
    Gradient following without back-propagation in layered networks
    Proceedings of the First IEEE Annual Conference on Neural Networks, San Diego, CA, June 1987, p. II-629-II-636.
    [pdf]
  • D.E.J. Blazis and J.W. Moore
    Simulation of a classically conditioned response: Components of the input trace and a cerebellar neural network implementation of the Sutton-Barto-Desmond model
    COINS Technical Report 87-74, University of Massachusetts, 1987.
  • S. Judd
    Learning in networks is hard
    Proceedings of the First IEEE Annual Conference on Neural Networks, San Diego, CA, June 1987.
  • J. S. Judd
    Complexity of connectionist learning with various node functions
    COINS Technical Report 87-60, University of Massachusetts, 1987.
  • N. A. Schmajuk and J. W. Moore
    Two attentional models of classical conditioning: Variations in CS effectiveness revisited
    COINS Technical Report 87-29, University of Massachusetts, 1987.
  • R. S. Sutton and A. G. Barto
    A temporal-difference model of classical conditioning
    Proceedings of the Ninth Annual Conference of the Cognitive Science Society, July, 1987.
    [pdf]

1986

  • A. G. Barto
    Game-theoretic cooperativity in networks of self-interested units
    Neural Networks for Computing, 151(1): 41-46, American Institute of Physics, New York, 1986.
    [pdf]
  • A. G. Barto, P. Anandan, and C. W. Anderson
    Cooperativity in networks of pattern recognizing stochastic learning automata
    Adaptive and Learning Systems: Theory and Applications, Plenum, New York, 1986.
    [pdf]
  • M. I. Jordan
    Attractor dynamics and parallelism in a connectionist sequential machine
    Proceedings of the Eighth Annual Conference of the Cognitive Science Society, Amherst, MA, 1986.
  • J. W. Moore, J. E. Desmond, N. E. Berthier, E. J. Blazis, R. S. Sutton and A. G. Barto
    Simulation of the classically conditioned nictitating membrane response by a neuron-like adaptive element. Response topography, neuronal firing, and interstimulus intervals.
    Behavioural Brain Research, 21:143-154, 1986.
    [pdf]

1985

  • A. G. Barto
    Adaptive neural networks for learning control: Some computational experiments
    Proceedings of the IEEE Workshop on Intelligent Control, Rensselaer Polytechnic Institute, Troy, NY, August 1985.
  • A. G. Barto
    Learning by statistical cooperation of self-interested neuron-like computing elements Human Neurobiology,4:229-256, 1985.
    [pdf]
  • A. G. Barto and P. Anandan
    Pattern recognizing stochastic learning automata
    IEEE Transactions on Systems, Man, and Cybernetics, 15:360-375, 1985.
    [pdf]
  • A. G. Barto and C. W. Anderson
    Structural learning in connectionist systems
    Proceedings of the Seventh Annual Conference of the Cognitive Science Society, Irvine, CA, August 1985.
  • O. Selfridge, R. S. Sutton and A. G. Barto
    Training and tracking in robotics
    Proceedings of the Ninth International Joint Conference on Artificial Intelligence, p. 670-672. San Mateo, CA: Morgan Kaufmann, 1985.
    [pdf]
  • R. S. Sutton and B. Pinette
    The learning of world models by connectionist networks
    Proceedings of the Seventh Annual Conference of the Cognitive Science Society, Irvine, CA, 1985.
    [pdf]
  • Moore, J., Desmond, J., Berthier, N., Blazis, D., Sutton, R.S., and Barto, A.G.
    Connectionist learning in real time: Sutton-Barto adaptive element and classical conditioning of the nictitating membrane response
    Seventh Annual Conference of the Cognitive Science Society, p. 318-322, 1985.
    [pdf]

1983

  • A. G. Barto and R. S. Sutton
    Neural problem solving
    COINS Technical Report 83-03, University of Massachusetts, 1983.
    [pdf ]
  • A. G. Barto, R. S. Sutton and C. W. Anderson
    Neuronlike elements that can solve difficult learning control problems
    IEEE Transactions on Systems, Man, and Cybernetics, 13:835-846, 1983.
    [pdf ]

1982

  • C. W. Anderson
    Feature generation and selection by a layered network of reinforcement learning elements: Some initial experiments.
    COINS Technical Report 82-12, University of Massachusetts, 1982.
  • A. G. Barto, C. W. Anderson, and R. S. Sutton
    Synthesis of nonlinear control surfaces by a layered associative search network
    Biological Cybernetics,43:175-185, 1982.
    [pdf ]
  • A. G. Barto and R. S. Sutton
    Simulation of anticipatory responses in classical conditioning by a neuron-like adaptive element
    Behavioural Brain Research, 4:221-235, 1982.
    [pdf ]
  • S. Bozinovski
    A self-learning system using secondary reinforcement.
    Cybernetics and Systems, Elsevier Science Publishers (North Holland), 1982.
  • A.G. Barto, R.S. Sutton, and C.W. Anderson
    Spatial learning simulation systems
    Proceedings of the 10th IMACS World Congress on Systems Simulation and Scientific Computation, pp. 204-206, 1982.

1981

  • A. G. Barto and R. S. Sutton
    Landmark learning: An illustration of associative search
    Biological Cybernetics,42:1-8, 1981.
    [pdf]
  • A. G. Barto, R. S. Sutton and P. S. Brouwer
    Associative search network: A reinforcement learning associative memory
    Biological Cybernetics,40:201-211, 1981.
    [pdf]
  • S. Bozinovski
    Teaching space: A representation concept for adaptive pattern classification
    COINS Technical Report 81-18, University of Massachusetts, 1981.
  • R. S. Sutton and A. G. Barto
    An adaptive network that constructs and uses an internal model of its environment
    Cognition and Brain Theory, 4:217-246, 1981.
    [pdf]
  • R. S. Sutton and A. G. Barto
    Toward a modern theory of adaptive networks: Expectation and prediction
    Psychological Review, 88:135-170, 1981.
    [pdf]
  • A. G. Barto and R.S. Sutton
    Goal seeking components for adaptive intelligence: An initial assessment
    AFWAL-TR-81-1070, Publisher Air Force Wright Aeronautical Laboratories, 1981.
    [pdf ]

1978

  • A. G. Barto
    Discrete and continuous models
    International Journal of General Systems, 4:163-177, 1978.
    [pdf]
  • A.G. Barto
    A note on pattern reproduction in tesselation structures
    Journal of Computer and Systems Sciences, 16:445-455, 1978.
    [pdf]
  • A.G. Barto
    Structurally invariant linear models of structurally varying linear systems
    Applied General Systems Research NATO Conference Series Volume 5, Springer, pp. 435-451, 1978.
    [ pdf ]