Sciweavers

215 search results - page 32 / 43
» Model-Based Reinforcement Learning with Continuous States an...
Sort
View
ISCIS
2009
Springer
14 years 3 months ago
Predicting future object states using learned affordances
Abstract—The notion of affordances was proposed by J.J. Gibson, to refer to the action possibilities offered to the organism by its environment. In a previous formalization, affo...
Emre Ugur, Erol Sahin, Erhan Oztop
AAAI
2006
13 years 10 months ago
Hard Constrained Semi-Markov Decision Processes
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 ...
Wai-Leong Yeow, Chen-Khong Tham, Wai-Choong Wong
IROS
2009
IEEE
142views Robotics» more  IROS 2009»
14 years 3 months ago
Phoneme acquisition model based on vowel imitation using Recurrent Neural Network
- A phoneme-acquisition system was developed using a computational model that explains the developmental process of human infants in the early period of acquiring language. There a...
Hisashi Kanda, Tetsuya Ogata, Toru Takahashi, Kazu...
CVPR
1999
IEEE
14 years 10 months ago
Time-Series Classification Using Mixed-State Dynamic Bayesian Networks
We present a novel mixed-state dynamic Bayesian network (DBN) framework for modeling and classifying timeseries data such as object trajectories. A hidden Markov model (HMM) of di...
Vladimir Pavlovic, Brendan J. Frey, Thomas S. Huan...
ECML
2006
Springer
14 years 12 days ago
Approximate Policy Iteration for Closed-Loop Learning of Visual Tasks
Abstract. Approximate Policy Iteration (API) is a reinforcement learning paradigm that is able to solve high-dimensional, continuous control problems. We propose to exploit API for...
Sébastien Jodogne, Cyril Briquet, Justus H....