De Aller-Bedste Bøger - over 12 mio. danske og engelske bøger
Levering: 1 - 2 hverdage
Hjælp
Login
  1. Forside
  2. Bøger
  3. Business og læring
  4. Computer og IT
  5. A Tutorial on Linear Function Approximators for Dynamic Programming and Reinforcement Learning

A Tutorial on Linear Function Approximators for Dynamic Programming and Reinforcement Learning

af Alborz Geramifard

indgår i Foundations and Trends (R) in Machine Learning serien

A Tutorial on Linear Function Approximators for Dynamic Programming and Reinforcement Learning af Alborz Geramifard
Bag om A Tutorial on Linear Function Approximators for Dynamic Programming and Reinforcement Learning

A Markov Decision Process (MDP) is a natural framework for formulating sequential decision-making problems under uncertainty. In recent years, researchers have greatly advanced algorithms for learning and acting in MDPs. This book reviews such algorithms.

Vis mere
  • Sprog:
  • Engelsk
  • ISBN:
  • 9781601987600
  • Indbinding:
  • Paperback
  • Sideantal:
  • 92
  • Udgivet:
  • 19. december 2013
  • Størrelse:
  • 156x234x5 mm.
  • Vægt:
  • 143 g.
  • 8-11 hverdage.
  • 6. december 2024

Normalpris

Abonnementspris

- Rabat på køb af fysiske bøger
- 1 valgfrit digitalt ugeblad
- 20 timers lytning og læsning
- Adgang til 70.000+ titler
- Ingen binding

Abonnementet koster 75 kr./md.
Ingen binding og kan opsiges når som helst.

Bag om Alborz Geramifard

Vis alle bøger af Alborz Geramifard

Beskrivelse af A Tutorial on Linear Function Approximators for Dynamic Programming and Reinforcement Learning

A Markov Decision Process (MDP) is a natural framework for formulating sequential decision-making problems under uncertainty. In recent years, researchers have greatly advanced algorithms for learning and acting in MDPs. This book reviews such algorithms.

Brugerbedømmelser af A Tutorial on Linear Function Approximators for Dynamic Programming and Reinforcement Learning



Andre købte også..
Find lignende bøger
Bogen A Tutorial on Linear Function Approximators for Dynamic Programming and Reinforcement Learning findes i følgende kategorier: