Learning automaton
≈ 3 min read
Names in other languages
No names in other languages are held for this entry yet.
Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.
A learning automaton is one type of machine learning algorithm studied since 1970s. Learning automata select their current action based on past experiences from the environment. It will fall into the range of reinforcement learning if the environment is stochastic and a Markov decision process (MDP) is used.
A learning automaton is one type of machine learning algorithm studied since 1970s. Learning automata select their current action based on past experiences from the environment. It will fall into the range of reinforcement learning if the environment is stochastic and a Markov decision process (MDP) is used. a set Φ = { Φ 1 , ..., Φ s } of possible internal states, a set α = { α 1 , ..., α r } of possible outputs, or actions, with r ≤ s, an initial state probability vector p(0) = ≪ p 1 (0), ..., p s (0) ≫, a computable function A which after each time step t generates p(t+1) from p(t), the current input, and the current state, and a function G: Φ → α which generates the output at each time step. In their paper, they investigate only stochastic automata with r = s and G being bijective, allowing them to confuse actions and states. The states of such an automaton correspond to the states of a "discrete-state discrete-parameter Markov process". At each time step t=0,1,2,3,..., the automaton reads an input from its environment, updates p(t) to p(t+1) by A, randomly chooses a successor state according to the probabilities p(t+1) and outputs the corresponding action. The automaton's environment, in turn, reads the action and sends the next input to the automaton. Frequently, the input set X = { 0,1 } is used, with 0 and 1 corresponding to a nonpenalty and a penalty response of the environment, respectively; in this case, the automaton should learn to minimize the number of penalty responses, and the feedback loop of automaton and environment is called a "P-model". More generally, a "Q-model" allows an arbitrary finite input set X, and an "S-model" uses the interval [0,1] of real numbers as X. A visualised demo / Art Work of a single Learning Automaton had been developed by μSystems (microSystems) Research Group at Newcastle University.
See also
Reinforcement learning Game theory Automata theory Philip Aranzulla and John Mellor (Home page): Mellor J and Aranzulla P (2000): "Using an S-Model Response Environment with Learnng [sic] Automata Based Routing Schemes for IP Networks ", Proc. Eighth IFIP Workshop on Performance Modelling and Evaluation of ATM and IP Networks, pp 56/1-56/12, Ilkley, UK. Aranzulla P and Mellor J (1997): "Comparing two routing algorithms requiring reduced signalling when applied to ATM networks", Proc. Fourteenth UK Teletraffic Symposium on Performance Engineering in Information Systems, pp 20/1-20/4, UMIST, Manchester, UK. Tsetlin M.L. Automation theory and modeling of biological systems. Academic Press; 1973.
References
Text derived from https://en.wikipedia.org/w/index.php?oldid=1338147086 under CC BY-SA 4.0; modifications have been made.