Items related to Reinforcement Learning with History Lists: Solving...
Reinforcement Learning with History Lists: Solving Partially Observable Decision Processes by Using Short Term Memory - Softcover
Synopsis
A very general framework for modeling uncertainty in learning environments is given by Partially observable Markov Decision Processes (POMDPs). In a POMDP setting, the learning agent infers a policy for acting optimally in all possible states of the environment, while receiving only observations of these states. The basic idea for coping with partial observability is to include memory into the representation of the policy. Perfect memory is provided by the belief space, i.e. the space of probability distributions over environmental states. However, computing policies defined on the belief space requires a considerable amount of prior knowledge about the learning problem and is expensive in terms of computation time.The author Stephan Timmer presents a reinforcement learning algorithm for solving POMDPs based on short term memory. In contrast to belief states, short term memory is not capable of representing optimal policies, but is far more practical and requires no prior knowledge about the learning problem. It can be shown that the algorithm can also be used to solve large Markov Decision Processes (MDPs) with continuous, multi-dimensional state spaces.
"synopsis" may belong to another edition of this title.
About the Author
Stephan Timmer, Dr. rer. nat.:Studium der Informatik an derUniversität Dortmund. Nach Abschluss der Diplomarbeit mehrjährigeTätigkeit als Wissenschaftlicher Mitarbeiter an der UniversitätOnsabrück mit Schwerpunkt Maschinelles Lernen und KünstlicheIntelligenz. Promotion im Jahr 2009.
"About this title" may belong to another edition of this title.
- PublisherSüdwestdeutscher Verlag für Hochschulschriften
- Publication date2009
- ISBN 10 3838106210
- ISBN 13 9783838106212
- BindingPaperback
- LanguageEnglish
- Number of pages160
Buy New
View this item
US$ 78.90
Shipping:
US$ 25.20
From Germany to U.S.A.
Search results for Reinforcement Learning with History Lists: Solving...
Seller Image
Reinforcement Learning with History Lists
Published by
Südwestdeutscher Verlag Für Hochschulschriften AG Co. KG Aug 2015, 2015
ISBN 10: 3838106210
ISBN 13: 9783838106212
New
Taschenbuch
Seller: BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Germany
Seller rating 5 out of 5 stars
Taschenbuch. Condition: Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -A very general framework for modeling uncertainty in learning environments is given by Partially observable Markov Decision Processes (POMDPs). In a POMDP setting, the learning agent infers a policy for acting optimally in all possible states of the environment, while receiving only observations of these states. The basic idea for coping with partial observability is to include memory into the representation of the policy. Perfect memory is provided by the belief space, i.e. the space of probability distributions over environmental states. However, computing policies defined on the belief space requires a considerable amount of prior knowledge about the learning problem and is expensive in terms of computation time.The author Stephan Timmer presents a reinforcement learning algorithm for solving POMDPs based on short term memory. In contrast to belief states, short term memory is not capable of representing optimal policies, but is far more practical and requires no prior knowledge about the learning problem. It can be shown that the algorithm can also be used to solve large Markov Decision Processes (MDPs) with continuous, multi-dimensional state spaces. 160 pp. Deutsch. Seller Inventory # 9783838106212
Quantity: 2 available
Seller Image
Reinforcement Learning with History Lists : Solving Partially Observable Decision Processes by Using Short Term Memory
Published by
Südwestdeutscher Verlag Für Hochschulschriften AG Co. KG, 2009
ISBN 10: 3838106210
ISBN 13: 9783838106212
New
Taschenbuch
Seller: AHA-BUCH GmbH, Einbeck, Germany
Seller rating 5 out of 5 stars
Taschenbuch. Condition: Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - A very general framework for modeling uncertainty in learning environments is given by Partially observable Markov Decision Processes (POMDPs). In a POMDP setting, the learning agent infers a policy for acting optimally in all possible states of the environment, while receiving only observations of these states. The basic idea for coping with partial observability is to include memory into the representation of the policy. Perfect memory is provided by the belief space, i.e. the space of probability distributions over environmental states. However, computing policies defined on the belief space requires a considerable amount of prior knowledge about the learning problem and is expensive in terms of computation time.The author Stephan Timmer presents a reinforcement learning algorithm for solving POMDPs based on short term memory. In contrast to belief states, short term memory is not capable of representing optimal policies, but is far more practical and requires no prior knowledge about the learning problem. It can be shown that the algorithm can also be used to solve large Markov Decision Processes (MDPs) with continuous, multi-dimensional state spaces. Seller Inventory # 9783838106212
Quantity: 1 available
Seller Image
Reinforcement Learning with History Lists
Published by
Südwestdeutscher Verlag für Hochschulschriften, 2015
ISBN 10: 3838106210
ISBN 13: 9783838106212
New
Softcover
Seller: moluna, Greven, Germany
Seller rating 5 out of 5 stars
Condition: New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. A very general framework for modeling uncertainty in learning environments is given by Partially observable Markov Decision Processes (POMDPs). In a POMDP setting, the learning agent infers a policy for acting optimally in all possible states of the environ. Seller Inventory # 5405008
Quantity: Over 20 available
Seller Image
Reinforcement Learning with History Lists | Solving Partially Observable Decision Processes by Using Short Term Memory
Published by
Südwestdeutscher Verlag für Hochschulschriften AG Co. KG, 2015
ISBN 10: 3838106210
ISBN 13: 9783838106212
New
Taschenbuch
Seller: preigu, Osnabrück, Germany
Seller rating 5 out of 5 stars
Taschenbuch. Condition: Neu. Reinforcement Learning with History Lists | Solving Partially Observable Decision Processes by Using Short Term Memory | Stephan Timmer | Taschenbuch | Paperback | 160 S. | Deutsch | 2015 | Südwestdeutscher Verlag für Hochschulschriften AG Co. KG | EAN 9783838106212 | Verantwortliche Person für die EU: Südwestdt. Verl. f. Hochschulschrift., Brivibas Gatve 197, 1039 RIGA, LETTLAND, customerservice[at]vdm-vsg[dot]de | Anbieter: preigu. Seller Inventory # 101624403
Quantity: 5 available