Sciweavers

1138 search results - page 47 / 228
» Feature Markov Decision Processes
Sort
View
ICIP
2008
IEEE
15 years 20 days ago
Activity-based temporal segmentation for videos of interacting objects using invariant trajectory features
This paper presents a content-based approach for temporal segmentation of videos. Tracked objects are characterized by their 2D trajectories which are used in a meaningful way to ...
Alexandre Hervieu, Patrick Bouthemy, Jean-Pierre L...
NIPS
2004
14 years 10 days 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
ICASSP
2008
IEEE
14 years 5 months ago
Rhetorical-State Hidden Markov Models for extractive speech summarization
We propose an extractive summarization system with a novel non-generative probabilistic framework for speech summarization. One of the most underutilized features in extractive su...
Pascale Fung, Ricky Ho Yin Chan, Justin Jian Zhang
ATAL
2006
Springer
14 years 2 months ago
On the relationship between MDPs and the BDI architecture
In this paper we describe the initial results of an investigation into the relationship between Markov Decision Processes (MDPs) and Belief-Desire-Intention (BDI) architectures. W...
Gerardo I. Simari, Simon Parsons
CORR
2010
Springer
105views Education» more  CORR 2010»
13 years 9 months ago
Optimism in Reinforcement Learning Based on Kullback-Leibler Divergence
We consider model-based reinforcement learning in finite Markov Decision Processes (MDPs), focussing on so-called optimistic strategies. Optimism is usually implemented by carryin...
Sarah Filippi, Olivier Cappé, Aurelien Gari...