Back to Results
First PageMeta Content
Operations research / Control theory / Equations / Mathematical optimization / Stochastic control / Reinforcement learning / Markov decision process / Bellman equation / Automated planning and scheduling / Statistics / Mathematics / Dynamic programming


Practical Solution Techniques for First-order MDPs ⋆ Scott Sanner ∗ Statistical Machine Learning Group National ICT Australia Canberra, ACT, 0200, Australia
Add to Reading List

Document Date: 2008-11-29 09:22:37

Open Document

File Size: 703,21 KB

Share Result on Facebook

City

Canberra / Rome / Paris / /

Currency

pence / /

/

Facility

Computer Science University of Toronto Toronto / /

IndustryTerm

known solution / stochastic dynamic programming algorithms / dynamic programming solution / constraint generation algorithm / term solution / symbolic dynamic programming solution / domain-independent solution / value iteration algorithm / linear programming solution / /

MusicAlbum

Bellman / /

Organization

Computer Science University of Toronto Toronto / Australia Craig Boutilier Department / /

Person

Scott Sanner / Tsitsiklis Roy / Van Roy / Craig Boutilier / /

Position

rt / model for decision-theoretic planning / planner / Corresponding author / /

Product

Pentax K-x Digital Camera / /

ProgrammingLanguage

V / /

Technology

constraint generation algorithm / stochastic dynamic programming algorithms / Machine Learning / artificial intelligence / 2.2 MDP Solution Algorithms / value iteration algorithm / /

SocialTag