1084 search results - page 92 / 217 » Hidden Markov Models with Multiple Observation Processes |
113
click to vote
COLT
2000
Springer
15 years 8 months ago
2000
Springer
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process ( ¢¡¤£¦¥§ ), and focus on gradient ascent approache...
116
click to vote
NIPS
2008
15 years 5 months ago
2008
Classical game theoretic approaches that make strong rationality assumptions have difficulty modeling human behaviour in economic games. We investigate the role of finite levels o...
143
click to vote
NIPS
2001
15 years 5 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...
127
click to vote
FLAIRS
2007
15 years 6 months ago
2007
We present a description of two small audio/visual immersive installations. The main framework is an interactive structure that enables multiple participants to generate jazz impr...
156
click to vote
ICIP
2003
IEEE
16 years 5 months ago
2003
IEEE
We present algorithms for automatic feature selection for unsupervised structure discovery from video sequences. Feature selection in this scenario is hard because of the absence ...