Rmax: A NearOptimal, Polynomial Time Reinforcement Learning Algorithm - PowerPoint PPT Presentation

1 / 49
} ?>
View by Category
About This Presentation
Title:

Rmax: A NearOptimal, Polynomial Time Reinforcement Learning Algorithm

Description:

Two airlines compete daily to supply transportation services to the US Army ... Theorem (impossibility): Given an imperfect monitoring setup, where the agent ... – PowerPoint PPT presentation

Number of Views:204
Avg rating:3.0/5.0
Slides: 50
Provided by: mas100
Category:

less

Write a Comment
User Comments (0)
About PowerShow.com