The Truck Backer-Upper: An Example of Self-Learning in Neural Networks

By W. Miller, Richard S. Sutton, Paul J. Werbos. 1995

How researchers see this paper

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

1. Greg Wayne
2. L. F. Abbott
3. Yoshua Bengio
4. Jason Aaron Edward Weston
5. Sergey Levine
6. J. Urgen Schmidhuber
7. Quoc V. Le
8. Andrea Soltoggio

Citations in the corpus

• Deep learning in neural networks: An overview (2014, methodology): “Decades ago, the method was used to learn to back up a model truck (Nguyen & Widrow, 1989).”
• Reinforcement learning by backpropagation through an LSTM model/critic (2007, unknown): “In the supervised learning version of backpropagation through a model [17], [7], [8], [11], desired outputs of the model (desired environmental states) are used to determine the errors that are to be backpropagated to the actor.”
• Hierarchical Control Using Networks Trained with Higher-Level Forward Models (2014, background): “This problem was first posed and solved by Nguyen and Widrow (1989), and their work is an early example of the successful solution of a nonlinear control problem by a neural network.”