output
20032026
most citedLSTM: A Search Space Odyssey

7.1k citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions
Showing 2015 · cs.AIShow all

1 paper · 2 filters

cs.AI2015★ 34 cited

On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models

Juergen Schmidhuber

This paper addresses the general problem of reinforcement learning (RL) in partially observable environments. In 2013, our large RL recurrent neural networks (RNNs) learned from sc…