Reinforcement learning by backpropagation through an LSTM model/critic

By Bram Bakker. 2007

30 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

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. Wojciech Samek
2. K. Müller
3. Grgoire Montavon
4. Sebastian Lapuschkin
5. Sepp Hochreiter
6. Christopher J. Anders
7. Leila Arras
8. Yonatan Belinkov

In Statistical and Nonlinear Physics

1. Grgoire Montavon
2. K. Müller
3. Sepp Hochreiter
4. Thomas Unterthiner
5. Wojciech Samek
6. José Antonio Arjona-Medina
7. Michael Widrich
8. Michael Gillhofer

Citations in the corpus

• RUDDER: Return Decomposition for Delayed Rewards (2018, background): “This is known as “backpropagation through a model” [22, 27, 28, 42, 33, 4, 5].”
• Explaining and Interpreting LSTMs (2019, methodology): “lready used in reinforcement learning [66] for advantage learning [7] and learning policies [27,50,28]. However, backward analysis via sensitivity analysis like \backpropagation through a model" [55,60,61,8] have major drawbacks: local minima, instabilities, exploding or vanishing gradients in ”