Episodic Reinforcement Learning by Logistic Reward-Weighted Regression.

Daan Wierstra Tom Schaul Jan Peters Jürgen Schmidhuber Episodic Reinforcement Learning by Logistic Reward-Weighted Regression. 407-416 2008 ICANN (1) http://dx.doi.org/10.1007/978-3-540-87536-9_42 conf/icann/2008-1 db/conf/icann/icann2008-1.html#WierstraSPS08