TD Learning with Constrained Gradients

By Ishan Durugkar, Peter Stone. 2018

17 citations recorded by the source corpus.

Subfields: Reinforcement Learning, Optimization & Training

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. Sergey Levine
2. Pieter Abbeel
3. Olivier Pietquin
4. R´emi Munos
5. Matteo Hessel
6. Hado van Hasselt
7. Marc G. Bellemare
8. Bilal Piot

In Optimization & Training

1. Olivier Pietquin
2. Matteo Hessel
3. Gabriel Barth-Maron
4. Todd Hester
5. R´emi Munos
6. Bilal Piot
7. David M. Budden
8. Tobias Pohlen

Citations in the corpus

• Observe and Look Further: Achieving Consistent Performance on Atari (2018, methodology): “Specifically, van Hasselt et al. [19] proposed PopArt and Durugkar and Stone [4] used constrained TD updates.”