210 search results - page 32 / 42 » An analysis of reinforcement learning with function approxim... |
104
click to vote
RSKT
2009
Springer
15 years 6 months ago
2009
Springer
A game-theoretic approach for learning optimal parameter values for probabilistic rough set regions is presented. The parameters can be used to define approximation regions in a p...
111
click to vote
ML
2002
ACM
14 years 11 months ago
2002
ACM
We provide an analytical comparison between discounted and average reward temporal-difference (TD) learning with linearly parameterized approximations. We first consider the asympt...
ALT
2009
Springer
15 years 8 months ago
2009
Springer
Abstract. We present the first (to our knowledge) approximation algorithm for tensor clustering—a powerful generalization to basic 1D clustering. Tensors are increasingly common...
109
click to vote
ICML
2006
IEEE
16 years 15 days ago
2006
IEEE
Policy evaluation is a critical step in the approximate solution of large Markov decision processes (MDPs), typically requiring O(|S|3 ) to directly solve the Bellman system of |S...
EC
2006
14 years 11 months ago
2006
The performance of a learning classifier system is due to its two main components. First, it evolves new structures by generating new rules in a genetic process; second, it adjust...