1176 search results - page 137 / 236 » Sparse reward processes |
151
click to vote
ATAL
2010
Springer
15 years 4 months ago
2010
Springer
PAC-MDP algorithms approach the exploration-exploitation problem of reinforcement learning agents in an effective way which guarantees that with high probability, the algorithm pe...
138
click to vote
CORR
2008
Springer
15 years 4 months ago
2008
Springer
We study the problem of dynamic spectrum sensing and access in cognitive radio systems as a partially observed Markov decision process (POMDP). A group of cognitive users cooperati...
142
click to vote
AMAI
2006
Springer
15 years 4 months ago
2006
Springer
A weakness of classical Markov decision processes (MDPs) is that they scale very poorly due to the flat state-space representation. Factored MDPs address this representational pro...
135
click to vote
JMLR
2006
15 years 4 months ago
2006
We propose a novel approach to optimize Partially Observable Markov Decisions Processes (POMDPs) defined on continuous spaces. To date, most algorithms for model-based POMDPs are ...
172
click to vote
NN
2006
Springer
15 years 4 months ago
2006
Springer
How does attention operate in natural scenes? We show that the receptive fields of inferior temporal cortex neurons that implement object representations become small and located ...