2011 search results - page 114 / 403 » Universal Reinforcement Learning |
136
click to vote
NIPS
2007
15 years 5 months ago
2007
We provide a provably efficient algorithm for learning Markov Decision Processes (MDPs) with continuous state and action spaces in the online setting. Specifically, we take a mo...
128
click to vote
EUSFLAT
2001
15 years 5 months ago
2001
The correction of angular misalignment between mating components is a fundamental requirement for their successful assembly. In this paper we present how a learning agent based on...
125
click to vote
ICML
2010
IEEE
15 years 5 months ago
2010
IEEE
We introduce new, efficient algorithms for value iteration with multiple reward functions and continuous state. We also give an algorithm for finding the set of all nondominated a...
145
click to vote
FLAIRS
2004
15 years 5 months ago
2004
er provides new techniques for abstracting the state space of a Markov Decision Process (MDP). These techniques extend one of the recent minimization models, known as -reduction, ...
116
click to vote
ICML
2006
IEEE
16 years 5 months ago
2006
IEEE
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...