May 24, 2019
In this paper, we introduce proximal gradient temporal difference learning, which provides a principled way of designing and analyzing true stochastic gradient temporal difference learning algorithms. We show how gradient TD (GTD) reinforcement learning methods can be formally derived, not by starting from their original objective functions, as previously attempted, but rather from a primal-dual saddle-point objective function. We also conduct a saddle-point error analysis to obtain finite-sample bounds on their performance. Previous analyses of this class of algorithms use stochastic approximation techniques to prove asymptotic convergence, and do not provide any finite-sample analysis. We also propose an accelerated algorithm, called GTD2-MP, that uses proximal “mirror maps” to yield an improved convergence rate. The results of our theoretical analysis imply that the GTD family of algorithms are comparable and may indeed be preferred over exist- ing least squares TD methods for off-policy learning, due to their linear complexity. We provide experimental results showing the improved performance of our accelerated gradient TD methods.
Written by
Mohammad Ghavamzadeh
Bo Liu
Ian Gemp
Ji Liu
Marek Petrik
Sridhar Mahadevan
Publisher
Journal of Artificial Intelligence Research
November 28, 2022
Nicolas Ballas, Bernhard Schölkopf, Chris Pal, Francesco Locatello, Li Erran, Martin Weiss, Nasim Rahaman, Yoshua Bengio
November 28, 2022
November 27, 2022
Andrea Tirinzoni, Aymen Al Marjani, Emilie Kaufmann
November 27, 2022
November 16, 2022
Kushal Tirumala, Aram H. Markosyan, Armen Aghajanyan, Luke Zettlemoyer
November 16, 2022
November 10, 2022
Unnat Jain, Abhinav Gupta, Himangi Mittal, Pedro Morgado
November 10, 2022
Product experiences
Foundational models
Product experiences
Latest news
Foundational models