Cargando…
A tutorial on linear function approximators for dynamic programming and reinforcement learning
This tutorial reviews techniques for planning and learning in Markov Decision Processes (MDPs) with linear function approximation of the value function. Two major paradigms for finding optimal policies were considered: dynamic programming (DP) techniques for planning and reinforcement learning (RL).
| Autores principales: | , , , , , |
|---|---|
| Lenguaje: | eng |
| Publicado: |
Now Publishers
2013
|
| Materias: | |
| Acceso en línea: | http://cds.cern.ch/record/2762208 |
| _version_ | 1780970663600717824 |
|---|---|
| author | Geramifard, Alborz Walsh, Thomas J Stefanie, Tellex Chowdhary, Girish Roy, Nicholas How, Jonathan P |
| author_facet | Geramifard, Alborz Walsh, Thomas J Stefanie, Tellex Chowdhary, Girish Roy, Nicholas How, Jonathan P |
| author_sort | Geramifard, Alborz |
| collection | CERN |
| description | This tutorial reviews techniques for planning and learning in Markov Decision Processes (MDPs) with linear function approximation of the value function. Two major paradigms for finding optimal policies were considered: dynamic programming (DP) techniques for planning and reinforcement learning (RL). |
| id | cern-2762208 |
| institution | Organización Europea para la Investigación Nuclear |
| language | eng |
| publishDate | 2013 |
| publisher | Now Publishers |
| record_format | invenio |
| spelling | cern-27622082021-04-21T16:39:13Zhttp://cds.cern.ch/record/2762208engGeramifard, AlborzWalsh, Thomas JStefanie, TellexChowdhary, GirishRoy, NicholasHow, Jonathan PA tutorial on linear function approximators for dynamic programming and reinforcement learningXXThis tutorial reviews techniques for planning and learning in Markov Decision Processes (MDPs) with linear function approximation of the value function. Two major paradigms for finding optimal policies were considered: dynamic programming (DP) techniques for planning and reinforcement learning (RL).Now Publishersoai:cds.cern.ch:27622082013 |
| spellingShingle | XX Geramifard, Alborz Walsh, Thomas J Stefanie, Tellex Chowdhary, Girish Roy, Nicholas How, Jonathan P A tutorial on linear function approximators for dynamic programming and reinforcement learning |
| title | A tutorial on linear function approximators for dynamic programming and reinforcement learning |
| title_full | A tutorial on linear function approximators for dynamic programming and reinforcement learning |
| title_fullStr | A tutorial on linear function approximators for dynamic programming and reinforcement learning |
| title_full_unstemmed | A tutorial on linear function approximators for dynamic programming and reinforcement learning |
| title_short | A tutorial on linear function approximators for dynamic programming and reinforcement learning |
| title_sort | tutorial on linear function approximators for dynamic programming and reinforcement learning |
| topic | XX |
| url | http://cds.cern.ch/record/2762208 |
| work_keys_str_mv | AT geramifardalborz atutorialonlinearfunctionapproximatorsfordynamicprogrammingandreinforcementlearning AT walshthomasj atutorialonlinearfunctionapproximatorsfordynamicprogrammingandreinforcementlearning AT stefanietellex atutorialonlinearfunctionapproximatorsfordynamicprogrammingandreinforcementlearning AT chowdharygirish atutorialonlinearfunctionapproximatorsfordynamicprogrammingandreinforcementlearning AT roynicholas atutorialonlinearfunctionapproximatorsfordynamicprogrammingandreinforcementlearning AT howjonathanp atutorialonlinearfunctionapproximatorsfordynamicprogrammingandreinforcementlearning AT geramifardalborz tutorialonlinearfunctionapproximatorsfordynamicprogrammingandreinforcementlearning AT walshthomasj tutorialonlinearfunctionapproximatorsfordynamicprogrammingandreinforcementlearning AT stefanietellex tutorialonlinearfunctionapproximatorsfordynamicprogrammingandreinforcementlearning AT chowdharygirish tutorialonlinearfunctionapproximatorsfordynamicprogrammingandreinforcementlearning AT roynicholas tutorialonlinearfunctionapproximatorsfordynamicprogrammingandreinforcementlearning AT howjonathanp tutorialonlinearfunctionapproximatorsfordynamicprogrammingandreinforcementlearning |