Efficient Learning in Cellular Simultaneous Recurrent Neural Networks - The Case of Maze Navigation Problem

By R. Ilin, Robert Thijs Kozma, Paul J. Werbos. 2007

27 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Computer Networks and Communications, Reinforcement Learning, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sergey Levine
2. Chelsea Finn
3. Pieter Abbeel
4. Yuxi Li
5. Matthew Botvinick
6. Yoshua Bengio
7. Ruslan Salakhutdinov
8. Charles Blundell

In Computational Theory and Mathematics

1. Matthew Botvinick
2. Dhruva Tirumala
3. Charles Blundell
4. Joel Z. Leibo
5. R´emi Munos
6. Sergey Levine
7. Marc G. Bellemare
8. Nicolas Manfred Otto Heess

In Computer Networks and Communications

1. R´emi Munos
2. Charles Blundell
3. Matthew Botvinick
4. Csaba Szepesvari
5. Aadirupa Saha
6. Tor Lattimore

In Reinforcement Learning

1. Sergey Levine
2. Pieter Abbeel
3. Chelsea Finn
4. Matthew Botvinick
5. Yuxi Li
6. Zeb Kurth-Nelson
7. Jane X. Wang
8. Charles Blundell

In Model Architectures

1. Zeb Kurth-Nelson
2. Joel Z. Leibo
3. R´emi Munos
4. Charles Blundell
5. Dharshan Kumaran
6. Jane X. Wang
7. Hubert Soyer
8. Matthew Botvinick

Citations in the corpus

• Learning to reinforcement learn (2016, methodology): “In particular, Ilin et al. (2007) showed that recurrent networks trained on random mazes can approximate dynamic programming procedures (see also Silver et al., 2017; Tamar et al., 2016).”