Sciweavers

91 search results - page 8 / 19
» Percentile Optimization for Markov Decision Processes with P...
Sort
View
GECCO
2009
Springer
162views Optimization» more  GECCO 2009»
13 years 5 months ago
Uncertainty handling CMA-ES for reinforcement learning
The covariance matrix adaptation evolution strategy (CMAES) has proven to be a powerful method for reinforcement learning (RL). Recently, the CMA-ES has been augmented with an ada...
Verena Heidrich-Meisner, Christian Igel
NIPS
2004
13 years 9 months ago
Learning first-order Markov models for control
First-order Markov models have been successfully applied to many problems, for example in modeling sequential data using Markov chains, and modeling control problems using the Mar...
Pieter Abbeel, Andrew Y. Ng
RSS
2007
176views Robotics» more  RSS 2007»
13 years 9 months ago
Active Policy Learning for Robot Planning and Exploration under Uncertainty
Abstract— This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested i...
Ruben Martinez-Cantin, Nando de Freitas, Arnaud Do...
ECAI
1998
Springer
13 years 12 months ago
Optimal Scheduling of Dynamic Progressive Processing
Progressive processing allows a system to satisfy a set of requests under time pressure by limiting the amount of processing allocated to each task based on a predefined hierarchic...
Abdel-Illah Mouaddib, Shlomo Zilberstein
EMMCVPR
2001
Springer
14 years 4 days ago
A Hierarchical Markov Random Field Model for Figure-Ground Segregation
To segregate overlapping objects into depth layers requires the integration of local occlusion cues distributed over the entire image into a global percept. We propose to model thi...
Stella X. Yu, Tai Sing Lee, Takeo Kanade