Adaptive Representations for Reinforcement Learning
This book presents new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seeks a control policy for a sequential decision task. Since current methods typically rely on manually designed solution representations, agents that automatically adapt their own r...
Saved in:
| Main Author: | |
|---|---|
| Format: | Livre numérique |
| Language: | Anglais |
| Published: |
Berlin, Heidelberg :
Springer Berlin Heidelberg
[20..].
Cham : Springer Nature |
| Edition: | 1st ed. 2010. |
| Series: | Studies in Computational Intelligence
291 |
| Online Access: | Accès sur la plateforme de l'éditeur Accès sur la plateforme Istex Accès Université d'Orléans Accès INSA CVL |
| Note: |
Archives Springer e-books (Licence nationale) Archives Springer e-books (Licence nationale) |
| Autres localisations: | Voir dans le Sudoc |
| Edition sous un autre format: | • Adaptive Representations for Reinforcement Learning, Texte imprimé, 9783642139314 • Adaptive Representations for Reinforcement Learning, Texte imprimé, 9783642422317 • Adaptive Representations for Reinforcement Learning, Texte imprimé, 9783642139314 • Adaptive Representations for Reinforcement Learning, Texte imprimé, 9783642139338 |
| LEADER | 04126nam a22003617a 4500 | ||
|---|---|---|---|
| 001 | 943281 | ||
| 008 | 110106q2000 xx ||| |||| 00| 0 eng d | ||
| 009 | PPN149075839 | ||
| 020 | |a 9783642139321 | ||
| 041 | 0 | |a eng | |
| 082 | |a 006.3 | ||
| 100 | 1 | |a Whiteson, Shimon. | |
| 245 | 1 | 0 | |a Adaptive Representations for Reinforcement Learning |c by Shimon Whiteson. |
| 250 | |a 1st ed. 2010. | ||
| 260 | |a Berlin, Heidelberg : |b Springer Berlin Heidelberg. | ||
| 260 | |a Cham : |b Springer Nature, |c [20..]. | ||
| 490 | 0 | |a Studies in Computational Intelligence |v 291 |x 1860-9503 | |
| 500 | |a Archives Springer e-books (Licence nationale) | ||
| 500 | |a Archives Springer e-books (Licence nationale) | ||
| 505 | 1 | |a Part 1 Introduction Part 2 Reinforcement Learning Part 3 On-Line Evolutionary Computation Part 4 Evolutionary Function Approximation Part 5 Sample-Efficient Evolutionary Function Approximation Part 6 Automatic Feature Selection for Reinforcement Learning Part 7 Adaptive Tile Coding Part 8 RelatedWork Part 9 Conclusion Part 10 Statistical Significance | |
| 506 | |a Accès en ligne pour les établissements français bénéficiaires des licences nationales | ||
| 506 | |a Accès soumis à abonnement pour tout autre établissement | ||
| 506 | |a Conditions particulières de réutilisation pour les bénéficiaires des licences nationales. https://www.licencesnationales.fr/springer-nature-ebooks-contrat-licence-ln-2017 | ||
| 520 | |a This book presents new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seeks a control policy for a sequential decision task. Since current methods typically rely on manually designed solution representations, agents that automatically adapt their own representations have the potential to dramatically improve performance. This book introduces two novel approaches for automatically discovering high-performing representations. The first approach synthesizes temporal difference methods, the traditional approach to reinforcement learning, with evolutionary methods, which can learn representations for a broad class of optimization problems. This synthesis is accomplished by customizing evolutionary methods to the on-line nature of reinforcement learning and using them to evolve representations for value function approximators. The second approach automatically learns representations based on piecewise-constant approximations of value functions. It begins with coarse representations and gradually refines them during learning, analyzing the current policy and value function to deduce the best refinements. This book also introduces a novel method for devising input representations. This method addresses the feature selection problem by extending an algorithm that evolves the topology and weights of neural networks such that it evolves their inputs too. In addition to introducing these new methods, this book presents extensive empirical results in multiple domains demonstrating that these techniques can substantially improve performance over methods with manual representations | ||
| 776 | 0 | |t Adaptive Representations for Reinforcement Learning |b Texte imprimé |z 9783642139314 | |
| 776 | 0 | |t Adaptive Representations for Reinforcement Learning |b Texte imprimé |z 9783642422317 | |
| 776 | 0 | |t Adaptive Representations for Reinforcement Learning |b Texte imprimé |z 9783642139314 | |
| 776 | 0 | |t Adaptive Representations for Reinforcement Learning |b Texte imprimé |z 9783642139338 | |
| 856 | 4 | |q PDF |u https://doi.org/10.1007/978-3-642-13932-1 |z Accès sur la plateforme de l'éditeur | |
| 856 | 4 | |u https://revue-sommaire.istex.fr/ark:/67375/8Q1-K58VWJQV-V |z Accès sur la plateforme Istex | |
| 856 | 4 | |5 452349901:747826994 |u https://ezproxy.univ-orleans.fr/login?url=https://dx.doi.org/10.1007/978-3-642-13932-1 |z Accès Université d'Orléans | |
| 856 | 4 | |5 180339901:750844205 |u https://ezproxy.insa-cvl.fr/login?qurl=https://dx.doi.org/10.1007/978-3-642-13932-1 |z Accès INSA CVL | |
| 997 | |0 943281 |1 Livre numérique |a Ressource numérique |b INSA |b ENSA |c 0/Bibliothèque numérique/ |c 1/Bibliothèque numérique/Autre ressource numérique/ | ||