Sciweavers

4242 search results - page 492 / 849
» An Event Spacing Experiment
Sort
View
IROS
2009
IEEE
206views Robotics» more  IROS 2009»
16 years 2 months ago
Bayesian reinforcement learning in continuous POMDPs with gaussian processes
— Partially Observable Markov Decision Processes (POMDPs) provide a rich mathematical model to handle realworld sequential decision processes but require a known model to be solv...
Patrick Dallaire, Camille Besse, Stéphane R...
174
Voted
IROS
2009
IEEE
149views Robotics» more  IROS 2009»
16 years 2 months ago
A shoe-integrated tactile display for directional navigation
— This paper proposes a novel wearable interface for the foot: an on-shoe tactile display that enables users to obtain information through the sense of touch of their feet. A 16-...
Ramiro Velazquez, Omar Bazan, Marco E. Magañ...
ISDA
2009
IEEE
16 years 2 months ago
Postponed Updates for Temporal-Difference Reinforcement Learning
This paper presents postponed updates, a new strategy for TD methods that can improve sample efficiency without incurring the computational and space requirements of model-based ...
Harm van Seijen, Shimon Whiteson
CAIP
2009
Springer
209views Image Analysis» more  CAIP 2009»
16 years 2 months ago
Smooth Multi-Manifold Embedding for Robust Identity-Independent Head Pose Estimation
In this paper, we propose a supervised Smooth Multi-Manifold Embedding (SMME) method for robust identity-independent head pose estimation. In order to handle the appearance variati...
Xiangyang Liu, Hongtao Lu, Heng Luo
EVOW
2010
Springer
16 years 2 months ago
A Directed Mutation Operator for Real Coded Genetic Algorithms
Abstract. Developing directed mutation methods has been an interesting research topic to improve the performance of genetic algorithms (GAs) for function optimization. This paper i...
Imtiaz Korejo, Shengxiang Yang, Changhe Li