Sciweavers

332 search results - page 31 / 67
» Ranking policies in discrete Markov decision processes
Sort
View
ICML
2006
IEEE
14 years 8 months ago
An analytic solution to discrete Bayesian reinforcement learning
Reinforcement learning (RL) was originally proposed as a framework to allow agents to learn in an online fashion as they interact with their environment. Existing RL algorithms co...
Pascal Poupart, Nikos A. Vlassis, Jesse Hoey, Kevi...
ICC
2007
IEEE
14 years 2 months ago
Dynamic Lightpath Establishment for Service Differentiation Based on Optimal MDP Policy in All-Optical Networks with Wavelength
— In this paper, we propose a dynamic lightpath establishment method for service differentiation in all-optical WDM networks with the capability of full-range wavelength conversi...
Takuji Tachibana, Shoji Kasahara, Kenji Sugimoto
NIPS
1996
13 years 9 months ago
Multidimensional Triangulation and Interpolation for Reinforcement Learning
Dynamic Programming, Q-learning and other discrete Markov Decision Process solvers can be applied to continuous d-dimensional state-spaces by quantizing the state space into an arr...
Scott Davies
ICML
2006
IEEE
14 years 8 months ago
Qualitative reinforcement learning
When the transition probabilities and rewards of a Markov Decision Process are specified exactly, the problem can be solved without any interaction with the environment. When no s...
Arkady Epshteyn, Gerald DeJong
ICRA
2007
IEEE
126views Robotics» more  ICRA 2007»
14 years 2 months ago
A formal framework for robot learning and control under model uncertainty
— While the Partially Observable Markov Decision Process (POMDP) provides a formal framework for the problem of robot control under uncertainty, it typically assumes a known and ...
Robin Jaulmes, Joelle Pineau, Doina Precup