Learning automata with changing number of actions
Read:: - [ ] Thathachar et al. (1987) - Learning automata with changing number of actions 🛫2023-11-06 !!2 rd citation todoist Print:: ❌ Zotero Link:: Zotero Files:: attachment pdf:: Thathachar_Harita_1987_Learning automata with changing number of actions.pdf Reading Note:: Web Rip:: url:: https://ieeexplore.ieee.org/abstract/document/6499323
TABLE without id
file.link as "Related Files",
title as "Title",
type as "type"
FROM "" AND -"ZZ. planning"
WHERE citekey = "thathacharLearningAutomataChanging1987"
SORT file.cday DESCAbstract
A reinforcement scheme that is based on the linear reward-inaction updating algorithm is presented for a learning automaton whose action set changes from instant to instant. A learning automaton using the algorithm is shown to be both absolutely expedient and ε-optimal. The simulation results verify the ε-optimality of the algorithm. The results can be extended to the design of general nonlinear absolutely expedient learning algorithms.