Matches in SemOpenAlex for { <https://semopenalex.org/work/W1497159557> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W1497159557 endingPage "213" @default.
- W1497159557 startingPage "189" @default.
- W1497159557 abstract "We present a computational case study of neuro-dynamic programming, a recent class of reinforcement learning methods. We cast the problem of play selection in American football as a stochastic shortest path Markov Decision Problem (MDP). In particular, we consider the problem faced by a quarterback in attempting to maximize the net score of an offensive drive. The resulting optimization problem serves as a medium-scale testbed for numerical algorithms based on policy iteration. The algorithms we consider evolve as a sequence of approximate policy evaluations and policy updates. An (exact) evaluation amounts to the computation of the rewardto-go function associated with the policy in question. Approximations of reward-to-go are obtained either as the solution or as a step toward the solution of a training problem involving simulated state/reward data pairs. Within this methodological framework there is a great deal of flexibility. In specifying a particular algorithm, one must select a parametric form for estimating the reward-to-go function as well as a training algorithm for tuning the approximation. One example we consider, among many others, is the use of a multilayer perceptron (i.e. neural network) which is trained by backpropagation. The objective of this paper is to illustrate the application of neuro-dynamic programming methods in solving a well-defined optimization problem. We will contrast and compare various algorithms mainly in terms of performance, although we will also consider complexity of implementation. Because our version of football leads to a medium-scale Markov decision problem, it is possible to compute the optimal solution numerically, providing a yardstick for meaningful comparison of the approximate methods." @default.
- W1497159557 created "2016-06-24" @default.
- W1497159557 creator A5039633806 @default.
- W1497159557 creator A5039911471 @default.
- W1497159557 date "1998-01-01" @default.
- W1497159557 modified "2023-09-23" @default.
- W1497159557 title "Play Selection in American Football: A Case Study in Neuro-Dynamic Programming" @default.
- W1497159557 cites W2009533501 @default.
- W1497159557 cites W2040766536 @default.
- W1497159557 cites W2081287319 @default.
- W1497159557 cites W2124599560 @default.
- W1497159557 cites W2149148771 @default.
- W1497159557 cites W2334782222 @default.
- W1497159557 cites W2787259794 @default.
- W1497159557 cites W4249345565 @default.
- W1497159557 cites W4362203700 @default.
- W1497159557 doi "https://doi.org/10.1007/978-1-4757-2807-1_7" @default.
- W1497159557 hasPublicationYear "1998" @default.
- W1497159557 type Work @default.
- W1497159557 sameAs 1497159557 @default.
- W1497159557 citedByCount "2" @default.
- W1497159557 countsByYear W14971595572023 @default.
- W1497159557 crossrefType "book-chapter" @default.
- W1497159557 hasAuthorship W1497159557A5039633806 @default.
- W1497159557 hasAuthorship W1497159557A5039911471 @default.
- W1497159557 hasConcept C105795698 @default.
- W1497159557 hasConcept C106189395 @default.
- W1497159557 hasConcept C11413529 @default.
- W1497159557 hasConcept C115988155 @default.
- W1497159557 hasConcept C119857082 @default.
- W1497159557 hasConcept C126255220 @default.
- W1497159557 hasConcept C14646407 @default.
- W1497159557 hasConcept C154945302 @default.
- W1497159557 hasConcept C159886148 @default.
- W1497159557 hasConcept C2780598303 @default.
- W1497159557 hasConcept C33923547 @default.
- W1497159557 hasConcept C37404715 @default.
- W1497159557 hasConcept C41008148 @default.
- W1497159557 hasConcept C50644808 @default.
- W1497159557 hasConcept C60908668 @default.
- W1497159557 hasConcept C97541855 @default.
- W1497159557 hasConceptScore W1497159557C105795698 @default.
- W1497159557 hasConceptScore W1497159557C106189395 @default.
- W1497159557 hasConceptScore W1497159557C11413529 @default.
- W1497159557 hasConceptScore W1497159557C115988155 @default.
- W1497159557 hasConceptScore W1497159557C119857082 @default.
- W1497159557 hasConceptScore W1497159557C126255220 @default.
- W1497159557 hasConceptScore W1497159557C14646407 @default.
- W1497159557 hasConceptScore W1497159557C154945302 @default.
- W1497159557 hasConceptScore W1497159557C159886148 @default.
- W1497159557 hasConceptScore W1497159557C2780598303 @default.
- W1497159557 hasConceptScore W1497159557C33923547 @default.
- W1497159557 hasConceptScore W1497159557C37404715 @default.
- W1497159557 hasConceptScore W1497159557C41008148 @default.
- W1497159557 hasConceptScore W1497159557C50644808 @default.
- W1497159557 hasConceptScore W1497159557C60908668 @default.
- W1497159557 hasConceptScore W1497159557C97541855 @default.
- W1497159557 hasLocation W14971595571 @default.
- W1497159557 hasOpenAccess W1497159557 @default.
- W1497159557 hasPrimaryLocation W14971595571 @default.
- W1497159557 hasRelatedWork W2156021013 @default.
- W1497159557 hasRelatedWork W2156992384 @default.
- W1497159557 hasRelatedWork W2168607500 @default.
- W1497159557 hasRelatedWork W2172425052 @default.
- W1497159557 hasRelatedWork W2373808749 @default.
- W1497159557 hasRelatedWork W2765742413 @default.
- W1497159557 hasRelatedWork W3165359854 @default.
- W1497159557 hasRelatedWork W4225977285 @default.
- W1497159557 hasRelatedWork W4281791088 @default.
- W1497159557 hasRelatedWork W4308702637 @default.
- W1497159557 isParatext "false" @default.
- W1497159557 isRetracted "false" @default.
- W1497159557 magId "1497159557" @default.
- W1497159557 workType "book-chapter" @default.