10 search results - page 2 / 2 » Learning Without State-Estimation in Partially Observable Ma... |
CDC
2008
IEEE
13 years 11 months ago
2008
IEEE
—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 cooper...
MOBICOM
2009
ACM
13 years 11 months ago
2009
ACM
The coexistence of two unlicensed links is considered, where one link interferes with the transmission of the other, over a timevarying, block-fading channel. In the absence of fa...
ICASSP
2008
IEEE
13 years 11 months ago
2008
IEEE
This paper presents a new framework for accumulating beliefs in spoken dialogue systems. The technique is based on updating a Bayesian Network that represents the underlying state...
GECCO
2009
Springer
13 years 2 months ago
2009
Springer
The covariance matrix adaptation evolution strategy (CMAES) has proven to be a powerful method for reinforcement learning (RL). Recently, the CMA-ES has been augmented with an ada...
ECML
2007
Springer
13 years 11 months ago
2007
Springer
We present Policy Gradient Actor-Critic (PGAC), a new model-free Reinforcement Learning (RL) method for creating limited-memory stochastic policies for Partially Observable Markov ...