2566 search results - page 9 / 514 » Relating reinforcement learning performance to classificatio... |
115
click to vote
MIR
2010
ACM
15 years 6 months ago
2010
ACM
This paper discusses two sets of automatic musical genre classification experiments. Promising research directions are then proposed based on the results of these experiments. The...
DATAMINE
2008
14 years 11 months ago
2008
Rules are commonly used for classification because they are modular, intelligible and easy to learn. Existing work in classification rule learning assumes the goal is to produce ca...
90
Voted
ICRA
2005
IEEE
15 years 5 months ago
2005
IEEE
— This paper presents a new reinforcement learning algorithm for accelerating acquisition of new skills by real mobile robots, without requiring simulation. It speeds up Q-learni...
ICML
2003
IEEE
15 years 4 months ago
2003
IEEE
Shaping can be an effective method for improving the learning rate in reinforcement systems. Previously, shaping has been heuristically motivated and implemented. We provide a for...
103
click to vote
AAAI
1998
15 years 1 months ago
1998
In this paper, we describe methods for e ciently computing better solutions to control problems in continuous state spaces. We provide algorithms that exploit online search to boo...