Normal view MARC view ISBD view

Algorithms for various cost criteria in reinforcement learning /

By:

Guin, Soumyajit

Contributor(s):

Advised by Bhatnagar, Shalabh

Material type: Text

TextLanguage: en Publication details: Bangalore : Indian Institute of Science, 2025.Description: vii, 75 p. : col. ill. e-Thesis 4.012 MbSubject(s):

DDC classification:

006.31 GUI

Online resources:

Click here to access online

Dissertation note: PhD;2025;Computer Science and Automation Summary: In this thesis we will look at various Reinforcement Learning algorithms. We will look at algorithms for various cost criteria or reward objectives namely Finite Horizon, Discounted Cost, Risk-Sensitive Cost. For Finite Horizon and Risk-Sensitive Cost we derive the policy gradient, and for Discounted Cost we propose a new algorithm called Critic-Actor. We analyze and prove the convergence for all the proposed algorithms. We also analyze the empirical performance of our algorithms through numerical experiments.

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings
Item type	Current library	Call number	URL	Status	Date due	Barcode
Thesis	JRD Tata Memorial Library	006.31 GUI (Browse shelf(Opens below))	Link to resource	Not for loan		ET00902

Includes bibliographical references

PhD;2025;Computer Science and Automation

In this thesis we will look at various Reinforcement Learning algorithms. We will look at algorithms for various cost criteria or reward objectives namely Finite Horizon, Discounted Cost, Risk-Sensitive Cost. For Finite Horizon and Risk-Sensitive Cost we derive the policy gradient, and for Discounted Cost we propose a new algorithm called Critic-Actor. We analyze and prove the convergence for all the proposed algorithms. We also analyze the empirical performance of our algorithms through numerical experiments.

There are no comments on this title.

to post a comment.