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...
Several marketing problems involve prediction of customer purchase behavior and forecasting future preferences. We consider predictive modeling of large scale, bi-modal or multimo...
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...
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...
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...