On the choice of subgoals for learning control systems
- 1 December 1968
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 13 (6) , 613-621
- https://doi.org/10.1109/tac.1968.1099032
Abstract
A subgoal problem is defined as the problem of choosing a subgoal or on-line performance evaluator compatible with reinforcement-type learning control systems. The subgoal must evaluate each control decision separately and direct the learning process toward the optimum with respect to the primary goal or performance index. Analytical results are presented for an unconstrained control, including an M-decision evaluator. This general subgoal fails to satisfy the conditions of per-decision evaluation except when M is 1, but might prove useful with different learning algorithms. A method is presented for "doing the best with what you have." That is, a priori information might be used either to design a fixed controller or to choose the subgoal for a learning controller. Analytical and experimental results demonstrate that as a general rule the learning controller makes the best use of the a priori knowledge.Keywords
This publication has 6 references indexed in Scilit:
- An algorithm for learning without external supervision and its application to learning control systemsIEEE Transactions on Automatic Control, 1966
- A variable structure automaton used as a multimodal searching techniqueIEEE Transactions on Automatic Control, 1966
- A discrete optimal control problemIEEE Transactions on Automatic Control, 1966
- A heuristic approach to reinforcement learning control systemsIEEE Transactions on Automatic Control, 1965
- On an inverse problem in optimal controlIEEE Transactions on Automatic Control, 1964
- Some Studies in Machine Learning Using the Game of CheckersIBM Journal of Research and Development, 1959