771 search results - page 71 / 155 » Markov Decision Processes with Arbitrary Reward Processes |
143
click to vote
JMLR
2008
15 years 4 months ago
2008
In this paper we develop a theoretical analysis of the performance of sampling-based fitted value iteration (FVI) to solve infinite state-space, discounted-reward Markovian decisi...
144
Voted
ICASSP
2010
IEEE
15 years 4 months ago
2010
IEEE
—We consider a cognitive radio network with distributed multiple secondary users, where each user independently searches for spectrum opportunities in multiple channels without e...
140
click to vote
ICC
2007
IEEE
15 years 10 months ago
2007
IEEE
We consider opportunistic spectrum access for secondary users over multiple channels whose occupancy by primary users is modeled as discrete-time Markov processes. Due to hardware...
131
click to vote
ICML
2006
IEEE
16 years 5 months ago
2006
IEEE
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
NIPS
2004
15 years 5 months ago
2004
We introduce a new algorithm based on linear programming that approximates the differential value function of an average-cost Markov decision process via a linear combination of p...