An adaptive optimal controller for discrete-time Markov environments

DOI10.1016/S0019-9958(77)90354-0zbMath0373.93025OpenAlexW2054940200MaRDI QIDQ4152423

Ian H. Witten

Publication date: 1977

Published in: Information and Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0019-9958(77)90354-0

Mathematics Subject Classification ID

Discrete-time Markov processes on general state spaces (60J05) Adaptive control/observation systems (93C40) Estimation and detection in stochastic control theory (93E10)

Related Items

Reinforcement Learning, Bit by Bit, Mathematical properties of neuronal TD-rules and differential Hebbian learning: a comparison, Basis function adaptation in temporal difference reinforcement learning, A Spiking Neural Network Model of an Actor-Critic Learning Agent, The convergence of \(TD(\lambda)\) for general \(\lambda\), Risk-averse autonomous systems: a brief history and recent developments from the perspective of optimal control