2108 search results - page 112 / 422 » Tracking in Reinforcement Learning |
EUSFLAT
2001
13 years 11 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...
ICML
2010
IEEE
13 years 11 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...
FLAIRS
2004
13 years 11 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, ...
ICML
2006
IEEE
14 years 10 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...
ICML
2000
IEEE
14 years 10 months ago
2000
IEEE
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...