113 search results - page 4 / 23 » Learning Representation and Control in Continuous Markov Dec... |
NIPS
2001
13 years 9 months ago
2001
We show that states of a dynamical system can be usefully represented by multi-step, action-conditional predictions of future observations. State representations that are grounded...
ICRA
2008
IEEE
14 years 2 months ago
2008
IEEE
— We consider the problem of optimal control in continuous and partially observable environments when the parameters of the model are not known exactly. Partially Observable Mark...
PAMI
2007
13 years 7 months ago
2007
—This paper presents a method for learning decision theoretic models of human behaviors from video data. Our system learns relationships between the movements of a person, the co...
ATAL
2008
Springer
13 years 9 months ago
2008
Springer
Meta-level control manages the allocation of limited resources to deliberative actions. This paper discusses efforts in adding meta-level control capabilities to a Markov Decision...
AAAI
2006
13 years 9 months ago
2006
In multiple criteria Markov Decision Processes (MDP) where multiple costs are incurred at every decision point, current methods solve them by minimising the expected primary cost ...