A feedback control structure for on-line learning tasks

Aronson, 1981 Barto, 1993, Learning to act using real-time dynamic programming Barto, 1983, Neuronlike adaptive elements that can solve difficult learning control problems, IEEE Transactions Systems Man, and Cybernetics Cyber, 13, 834, 10.1109/TSMC.1983.6313077 Bruner, 1973, Organization of early skilled action, Child Development, 44, 1, 10.2307/1127671 Coelho, 1994, Effective multifingered grasp synthesis Connolly, 1994, Harmonic functions and collision probabilities Connolly, 1993, The applications of harmonic functions to robotics, Journal of Robotic Systems, 10, 931, 10.1002/rob.4620100704 Crites, 1995, Improving elevator performance using reinforcement learning, Vol. 8 Millán, 1996, Rapid, safe and incremental learning of navigation strategies, IEEE Transactions Systems Man, and Cybernetic, 26, 408, 10.1109/3477.499792 Grupen, 1995, Distributed control representation for manipulation tasks, IEEE Expert, 10, 9, 10.1109/64.395356 Grupen, 1993, Manipulability-based spatial isotropy: A kinematic reflex Gullapalli, 1992, Learning reactive admittance control, 1475 Hoff, 1996, An architecture for behavior coordination learning, 2375 Huber, 1996, A hybrid discrete event dynamic systems approach to robot control Huber, 1996, A control basis for multilegged walking, Vol. 4, 2988 Košecká, 1994, Application of discrete event systems for modeling and controlling robotic agents, 2557 Maes, 1990, Learning to coordinate behaviors Mahadevan, 1992, Automatic programming of behavior-based robots using reinforcement learning, Artificial Intelligence, 55, 311, 10.1016/0004-3702(92)90058-6 Moore, 1993, Prioritized sweeping: Reinforcement learning with less data and less real time, Machine Learning, 13, 10.1007/BF00993104 Özveren, 1990, Observability of discrete event dynamic systems, IEEE Transactions on Automatic Control, 35, 797, 10.1109/9.57018 Piaget, 1952 Raibert, 1981, Hybrid position/force control of manipulators, Journal of Dynamic Systems, Measurements, and Control, 102, 127 Ramadge, 1989, The control of discrete event systems, 77, 81 Singh, 1994, Robust reinforcement learning in motion planning, 6 Sobh, 1994, A subject-indexed bibliography of discrete event dynamic systems, IEEE Robotics and Automation Magazine, 1, 14, 10.1109/100.298482 Stiver, 1996, A logical approach to the design of hybrid systems, Mathematical and Computer Modelling, 27, 55, 10.1016/0895-7177(96)00064-7 Sutton, 1990, First results with Dyna, an integrated architecture for learning, planning and reacting, 179 Watkins, 1992, Technical note: Q-learning, Machine Learning, 8, 279, 10.1023/A:1022676722315 Watkins, 1989, Learning from delayed rewards Yoshikawa, 1990