523 search results - page 60 / 105 » Structured Solution Methods for Non-Markovian Decision Proce... |
133
click to vote
UAI
2008
15 years 5 months ago
2008
Approximate linear programming (ALP) is an efficient approach to solving large factored Markov decision processes (MDPs). The main idea of the method is to approximate the optimal...
114
click to vote
ISF
2007
15 years 3 months ago
2007
This article discusses methods to support assurance of surveillance monitoring; and compliance verification knowledge management (CV-KM). The discussion includes aspects of primar...
139
Voted
ICRA
2007
IEEE
15 years 10 months ago
2007
IEEE
— The least squares approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular an...
108
click to vote
ATAL
1997
Springer
15 years 8 months ago
1997
Springer
Many agent-based systems rely for their effectiveness on the intelligence of individual agents, and interaction among agents is required simply to coordinate these individually com...
165
Voted
JMLR
2010
14 years 10 months ago
2010
In this paper, we propose a novel adaptive step-size approach for policy gradient reinforcement learning. A new metric is defined for policy gradients that measures the effect of ...