3628 search results - page 190 / 726 » The Decision Diffie-Hellman Problem |
109
Voted
COLT
2000
Springer
15 years 7 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...
121
Voted
COLT
2004
Springer
15 years 7 months ago
2004
Springer
This paper introduces a new method using dyadic decision trees for estimating a classification or a regression function in a multiclass classification problem. The estimator is bas...
119
Voted
ECAI
2004
Springer
15 years 7 months ago
2004
Springer
In this paper, we tackle the satisfiability problem for multi-context systems. First, we establish a satisfiability algorithm based on an encoding into propositional logic. Then, w...
131
click to vote
ECML
2006
Springer
15 years 7 months ago
2006
Springer
Abstract. For large state-space Markovian Decision Problems MonteCarlo planning is one of the few viable approaches to find near-optimal solutions. In this paper we introduce a new...
132
Voted
NIPS
2004
15 years 4 months ago
2004
Existing algorithms for discrete partially observable Markov decision processes can at best solve problems of a few thousand states due to two important sources of intractability:...