Punish/Reward: Learning with a Critic in Adaptive Threshold Systems

DOI10.1109/TSMC.1973.4309272zbMath0281.68041MaRDI QIDQ4766611

Sidhartha Maitra, Narendra K. Gupta, Bernard Widrow

Publication date: 1973

Published in: IEEE Transactions on Systems, Man, and Cybernetics (Search for Journal in Brave)

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Related Items (14)

A recurrent neural network controller and learning algorithm for the on- line learning control of autonomous underwater vehicles ⋮ A comparison of adaptive critic and chemotaxis methods in adaptive control ⋮ Neurocontrol: A literature survey ⋮ Event-triggered constrained control with DHP implementation for nonaffine discrete-time systems ⋮ Neural-net computing and the intelligent control of systems ⋮ Adaptive critic designs for optimal control of uncertain nonlinear systems with unmatched interconnections ⋮ Associative search network: A reinforcement learning associative memory ⋮ Reinforcement learning algorithms with function approximation: recent advances and applications ⋮ Totally model-free actor-critic recurrent neural-network reinforcement learning in non-Markovian domains ⋮ Optimal design of a driver assistance controller based on surrounding vehicle's social behavior game model ⋮ Theory construction in psychology: The interpretation and integration of psychological data ⋮ Cerebral mechanism for reward-mediated learning: A mathematical model of neuropopulational network plasticity ⋮ Optimality and convergence of adaptive optimal control by reinforcement synthesis ⋮ Linear function neurons: Structure and training

This page was built for publication: Punish/Reward: Learning with a Critic in Adaptive Threshold Systems