2108 search results - page 178 / 422 » Tracking in Reinforcement Learning |
103
click to vote
ATAL
2008
Springer
15 years 4 months ago
2008
Springer
The goal of Reinforcement learning (RL) is to maximize reward (minimize cost) in a Markov decision process (MDP) without knowing the underlying model a priori. RL algorithms tend ...
126
Voted
AAAI
2006
15 years 4 months ago
2006
In this paper we propose a model for human learning and decision making in environments of repeated Cliff-Edge (CE) interactions. In CE environments, which include common daily in...
142
Voted
ICML
2010
IEEE
15 years 18 days ago
2010
IEEE
Temporal difference (TD) algorithms are attractive for reinforcement learning due to their ease-of-implementation and use of "bootstrapped" return estimates to make effi...
141
Voted
VR
2010
IEEE
15 years 1 months ago
2010
IEEE
Tracking is a major issue of virtual and augmented reality applications. Single object tracking on monocular video streams is fairly well understood. However, when it comes to mul...
168
Voted
CVPR
2010
IEEE
15 years 10 months ago
2010
IEEE
We propose a method that rates the suitability of given templates for template-based tracking in real-time. This is important for applications with online template selection, such...