223 search results - page 18 / 45 » Least-Squares Temporal Difference Learning |
ICML
2009
IEEE
14 years 9 months ago
2009
IEEE
We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable en...
ICDM
2008
IEEE
14 years 3 months ago
2008
IEEE
Several marketing problems involve prediction of customer purchase behavior and forecasting future preferences. We consider predictive modeling of large scale, bi-modal or multimo...
GECCO
2009
Springer
14 years 1 months ago
2009
Springer
We apply CMA-ES, an evolution strategy with covariance matrix adaptation, and TDL (Temporal Difference Learning) to reinforcement learning tasks. In both cases these algorithms se...
ML
1998
ACM
13 years 8 months ago
1998
ACM
Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of t...
ICONIP
2009
13 years 6 months ago
2009
Reinforcement learning induces non-stationarity at several levels. Adaptation to non-stationary environments is of course a desired feature of a fair RL algorithm. Yet, even if the...