Showing papers on "Reinforcement learning published in 1986"

Learning Control Systems-Review and Outlook

Abstract: The basic concept of learning control is introduced. The following five learning schemes are briefly reviewed: 1) trainable controllers using pattern classifiers, 2) reinforcement learning control systems, 3) Bayesian estimation, 4) stochastic approximation, and 5) stochastic automata models. Potential applications and problems for further research in learning control are outlined.

Learning and Problem Solving with Multilayer Connectionist Systems

Abstract: THE DIFFICULTIES OF LEARNING IN MULTILAYERED NETWORKS OF COMPUTATIONAL UNITS HAS LIMITED THE USE OF CONNECTIONIST SYSTEMS IN COMPLEX DOMAINS. THIS DISSERTATION ELUCIDATES THE ISSUES OF LEARNING IN A NETWORK''S HIDDEN UNITS, AND REVIEWS METHODS FOR ADDRESSING THESE ISSUES THAT HAVE BEEN DEVELOPED THROUGH THE YEARS. ISSUES OF LEARNING IN HIDDEN UNITS ARE SHOWN TO BE ANALOGOUS TO LEARNING ISSUES FOR MULTILAYER SYSTEMS EMPLOYING SYMBOLIC REPRSENTATIONS. COMPARISONS OF A NUMBER OF ALGORITHMS FOR LEARNING IN HIDDEN UNITS ARE MADE BY APPLYING THEM IN A CONSISTENT MANNER TO SEVERAL TASKS. RECENTLY DEVELOPED ALGORITHMS, INCLUDING RUMELHART, ET AL''S, ERROR BACK-PROPOGATIONS ALGORITHM AND BARTO, ET AL''S, REINFORCEMENT-LEARNING ALGORITHMS, LEARN THE SOLUTIONS TO THE TASKS MUCH MORE SUCCESSFULLY THAN METHODS OF THE PAST. A NOVEL ALGORITHM IS EXAMINED THAT COMBINES ASPECTS OF REINFORCEMENT LEARNING AND A DATA-DIRECTED SEARCH FOR USEFUL WEIGHTS, AND IS SHOWN TO OUT PERFORM REINFORMCEMENT-LEARNING ALGORITHMS. A CONNECTIONIST FRAMEWORK FOR THE LEARNING OF STRATEGIES IS DESCRIBED WHICH COMBINES THE ERROR BACK-PROPOGATION ALGORITHM FOR LEARNING IN HIDDEN UNITS WITH SUTTON''S AHC ALGORITHM TO LEARN EVALUATION FUNCTIONS AND WITH A REINFORCEMENT-LEARNING ALGORITHM TO LEARN SEARCH HEURISTICS. THE GENERAL- ITY OF THIS HYBRID SYSTEM IS DEMONSTRATED THROUGH SUCCESSFUL APPLICATIONS

Cooperativity in Networks of Pattern Recognizing Stochastic Learning Automata

Abstract: A class of learning tasks is described that combines aspects of learning automaton tasks and supervised learning pattern-classification tasks. We call these associative reinforcement learning tasks. An algorithm is presented, called the associative reward-penalty, or A R−P , algorithm, for which a form of optimal performance has been proved. This algorithm simultaneously generalizes a class of stochastic learning automata and a class of supervised learning pattern-classification methods. Simulation results are presented that illustrate the associative reinforcement learning task and the performance of the the A R−P algorithm. Additional simulation results are presented showing how cooperative activity in networks of interconnected A R−P automata can olve difficult nonlinear associative learning problems.