Sciweavers

9521 search results - page 343 / 1905
» Compiling with continuations, continued
Sort
View
ICML
2009
IEEE
16 years 4 months ago
Binary action search for learning continuous-action control policies
Reinforcement Learning methods for controlling stochastic processes typically assume a small and discrete action space. While continuous action spaces are quite common in real-wor...
Jason Pazis, Michail G. Lagoudakis
WINE
2009
Springer
179views Economy» more  WINE 2009»
15 years 10 months ago
Betting on the Real Line
We study the problem of designing prediction markets for random variables with continuous or countably infinite outcomes on the real line. Our interval betting languages allow tra...
Xi Gao, Yiling Chen, David M. Pennock
IROS
2008
IEEE
161views Robotics» more  IROS 2008»
15 years 10 months ago
Segmenting acoustic signal with articulatory movement using Recurrent Neural Network for phoneme acquisition
— This paper proposes a computational model for phoneme acquisition by infants. Human infants perceive speech sounds not as discrete phoneme sequences but as continuous acoustic ...
Hisashi Kanda, Tetsuya Ogata, Kazunori Komatani, H...
ACSC
2007
IEEE
15 years 10 months ago
Mutually Visible Agents in a Discrete Environment
As computer controlled entities are set to move and explore more complex environments they need to be able to perform navigation tasks, like finding minimal cost routes. Much wor...
Joel Fenwick, Vladimir Estivill-Castro
HYBRID
2007
Springer
15 years 10 months ago
Robust, Optimal Predictive Control of Jump Markov Linear Systems Using Particles
Hybrid discrete-continuous models, such as Jump Markov Linear Systems, are convenient tools for representing many real-world systems; in the case of fault detection, discrete jumps...
Lars Blackmore, Askar Bektassov, Masahiro Ono, Bri...