Back to Results
First PageMeta Content
Concurrency control / Concurrency / Reinforcement learning / Markov decision process / Thread / Q-learning / Monitor / Deadlock / SARSA / Statistics / Computing / Mathematics


Concurrent Hierarchical Reinforcement Learning Bhaskara Marthi, Stuart Russell, David Latham Computer Science Division University of California Berkeley, CA 94720 {bhaskara,russell,latham}@cs.berkeley.edu
Add to Reading List

Document Date: 2005-04-15 21:04:50

Open Document

File Size: 144,54 KB

Share Result on Facebook

City

Shaping Potential / /

Company

Neural Information Processing Systems / /

/

Facility

Computer Science Carnegie Mellon University / Town Hall / David Latham Computer Science Division University of California Berkeley / /

IndustryTerm

graph using cost network / multieffector systems / /

Organization

University of California / David Latham Computer Science Division University / Carlos Guestrin School of Computer Science Carnegie Mellon University Pittsburgh / UC Berkeley / /

Person

Parr / Andre / Train Footmen (Barracks) / Stuart Russell / David Latham / /

/

Position

scheduler / scheduler / and consider the following random process / player / designer / external scheduler / programmer / /

ProgrammingLanguage

Lisp / /

Technology

hierarchical Q-learning algorithm / same algorithm / Q-learning algorithm / decomposed SARSA algorithm / /

URL

stratagus.sourceforge.net / http /

SocialTag