Sciweavers

34 search results - page 1 / 7
» Action Elimination and Stopping Conditions for Reinforcement...
Sort
View
ICML
2003
IEEE
14 years 4 months ago
Action Elimination and Stopping Conditions for Reinforcement Learning
We consider incorporating action elimination procedures in reinforcement learning algorithms. We suggest a framework that is based on learning an upper and a lower estimates of th...
Eyal Even-Dar, Shie Mannor, Yishay Mansour
ICML
2007
IEEE
14 years 4 months ago
Conditional random fields for multi-agent reinforcement learning
Conditional random fields (CRFs) are graphical models for modeling the probability of labels given the observations. They have traditionally been trained with using a set of obser...
Xinhua Zhang, Douglas Aberdeen, S. V. N. Vishwanat...
ICML
2009
IEEE
14 years 4 months ago
Binary action search for learning continuous-action control policies
Reinforcement Learning methods for controlling stochastic processes typically assume a small and discrete action space. While continuous action spaces are quite common in real-wor...
Jason Pazis, Michail G. Lagoudakis
ECAI
2006
Springer
13 years 7 months ago
Learning by Automatic Option Discovery from Conditionally Terminating Sequences
Abstract. This paper proposes a novel approach to discover options in the form of conditionally terminating sequences, and shows how they can be integrated into reinforcement learn...
Sertan Girgin, Faruk Polat, Reda Alhajj
AIPS
2010
13 years 6 months ago
Action Elimination and Plan Neighborhood Graph Search: Two Algorithms for Plan Improvement
Compared to optimal planners, satisficing planners can solve much harder problems but may produce overly costly and long plans. Plan quality for satisficing planners has become in...
Hootan Nakhost, Martin Müller 0003