Neural networks for control

By W. Miller, Richard S. Sutton, Paul J. Werbos. 1990

Subfields: Reinforcement Learning

How researchers see this paper

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

In Reinforcement Learning

1. Yoshua Bengio
2. Sergey Levine
3. Joelle Pineau
4. Shimon Whiteson
5. Anirudh Goyal
6. Warrren B Powell
7. Pieter Abbeel
8. Mitsuo Kawato

Citations in the corpus

• An Actor-Critic Algorithm for Sequence Prediction (2016, methodology): “. To train the critic, we adapt the temporal difference methods from the RL literature (Sutton, 1988) to our setup. While RL methods with non-linear function approximators are not new (Tesauro, 1994; Miller et al., 1995), they have recently surged in popularity, giving rise to the field of ‘deep RL’ ”
• A computational model of four regions of the cerebellum based on feedback-error learning (2004, background): “How can an internal inverse model be acquired? If a computational "teacher" can provide the correct motor commands, motor learning can be done in the framework of the Widrow-Hoff rule (1960), consistent with biologically demonstrable heterosynaptic plasticity processes ( Barto 1990 ).”
• Efficient robust policy optimization (2012, background): “One area of reinforcement learning that is also closely related to this work is that of adaptive critics [26]–[31].”
• Handbook of Learning and Approximate Dynamic Programming (IEEE Press Series on Computational Intelligence) (2004, background): “We note that [59] also uses the term ‘adaptive’ in this latter sense.”