Decentralized learning in finite Markov chains
From MaRDI portal
Publication:3734188
DOI10.1109/TAC.1986.1104342zbMath0598.90092OpenAlexW2101130101MaRDI QIDQ3734188
Kumpati S. Narendra, Richard M. Wheeler
Publication date: 1986
Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1109/tac.1986.1104342
decentralized controllearning automatafinite Markov chainsunknown transition probabilities and rewards
Learning and adaptive systems in artificial intelligence (68T05) Cooperative games (91A12) Adaptive control/observation systems (93C40) Discrete-time control/observation systems (93C55) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)
Related Items
Multi-agent zero-sum differential graphical games for disturbance rejection in distributed control, Reinforcement learning control using interconnected learning automata, Adaptive control of Markov chains with local updates, Analyzing the dynamics of stigmergetic interactions through pheromone games, Learning automata based multi‐agent system algorithms for finding optimal policies in Markov games, Simple statistical gradient-following algorithms for connectionist reinforcement learning, Learning models for decentralized decision making, Adaptive approaches to stochastic programming, Absolutely expedient algorithms for learning Nash equilibria
