Sciweavers

3628 search results - page 190 / 726
» The Decision Diffie-Hellman Problem
Sort
View
COLT
2000
Springer
15 years 10 months ago
Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process (  ¢¡¤£¦¥§  ), and focus on gradient ascent approache...
Peter L. Bartlett, Jonathan Baxter
COLT
2004
Springer
15 years 10 months ago
Oracle Bounds and Exact Algorithm for Dyadic Classification Trees
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...
Gilles Blanchard, Christin Schäfer, Yves Roze...
ECAI
2004
Springer
15 years 10 months ago
Many Hands Make Light Work: Localized Satisfiability for Multi-Context Systems
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...
Floris Roelofsen, Luciano Serafini, Alessandro Cim...
ECML
2006
Springer
15 years 10 months ago
Bandit Based Monte-Carlo Planning
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...
Levente Kocsis, Csaba Szepesvári
NIPS
2004
15 years 7 months ago
VDCBPI: an Approximate Scalable Algorithm for Large POMDPs
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:...
Pascal Poupart, Craig Boutilier