2566 search results - page 1 / 514 » Relating reinforcement learning performance to classificatio... |
ICML
2005
IEEE
14 years 11 months ago
2005
IEEE
We prove a quantitative connection between the expected sum of rewards of a policy and binary classification performance on created subproblems. This connection holds without any ...
GECCO
2004
Springer
14 years 4 months ago
2004
Springer
This paper introduces a gradient-based reward prediction update mechanism to the XCS classifier system as applied in neuralnetwork type learning and function approximation mechani...
CSE
2009
IEEE
14 years 5 months ago
2009
IEEE
This paper describes a method of applying a reinforcement learning artificial intelligence to categorize audio files by mood based on listener response during a performance. The s...
ICML
2005
IEEE
14 years 11 months ago
2005
IEEE
This paper is concerned with the problem of predicting relative performance of classification algorithms. It focusses on methods that use results on small samples and discusses th...
KCAP
2005
ACM
14 years 4 months ago
2005
ACM
We present a framework for knowledge transfer from one reinforcement learning task to a related task through advicetaking mechanisms. We discuss the importance of transfer in comp...