Sciweavers

2 search results - page 1 / 1
» Co-evolving recurrent neurons learn deep memory POMDPs
Sort
View
GECCO
2005
Springer
155views Optimization» more  GECCO 2005»
14 years 28 days ago
Co-evolving recurrent neurons learn deep memory POMDPs
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
Faustino J. Gomez, Jürgen Schmidhuber
ICANN
2007
Springer
14 years 1 months ago
Solving Deep Memory POMDPs with Recurrent Policy Gradients
Abstract. This paper presents Recurrent Policy Gradients, a modelfree reinforcement learning (RL) method creating limited-memory stochastic policies for partially observable Markov...
Daan Wierstra, Alexander Förster, Jan Peters,...