3274 search results - page 425 / 655 » Using Learning in a Control Agent |
163
Voted
ECML
2006
Springer
15 years 6 months ago
2006
Springer
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
143
Voted
COLT
2010
Springer
15 years 16 days ago
2010
Springer
In standard online learning, the goal of the learner is to maintain an average loss that is "not too big" compared to the loss of the best-performing function in a fixed...
114
click to vote
JSS
2007
15 years 2 months ago
2007
Without rigorous software development and maintenance, software tends to lose its original architectural structure and become difficult to understand and modify. ArchJava, a recen...
102
click to vote
SBIA
2004
Springer
15 years 7 months ago
2004
Springer
Abstract. Most of the work in machine learning assume that examples are generated at random according to some stationary probability distribution. In this work we study the problem...
136
click to vote
NIPS
1996
15 years 3 months ago
1996
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...