| dc.contributor.advisor | Bhatnagar, Shalabh | |
| dc.contributor.author | Guin, Soumyajit | |
| dc.date.accessioned | 2025-04-16T05:24:17Z | |
| dc.date.available | 2025-04-16T05:24:17Z | |
| dc.date.submitted | 2025 | |
| dc.identifier.uri | https://etd.iisc.ac.in/handle/2005/6892 | |
| dc.description.abstract | 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. | en_US |
| dc.language.iso | en_US | en_US |
| dc.relation.ispartofseries | ;ET00902 | |
| dc.rights | I grant Indian Institute of Science the right to archive and to make available my thesis or dissertation in whole or in part in all forms of media, now hereafter known. I retain all proprietary rights, such as patent rights. I also retain the right to use in future works (such as articles or books) all or part
of this thesis or dissertation | en_US |
| dc.subject | Reinforcement Learning | en_US |
| dc.subject | algorithms | en_US |
| dc.subject | Finite Horizon | en_US |
| dc.subject | Risk-Sensitive Cost | en_US |
| dc.subject | Discounted Cost | en_US |
| dc.subject | Critic-Actor Algorithm | en_US |
| dc.subject | Convergence | en_US |
| dc.subject.classification | Research Subject Categories::TECHNOLOGY::Information technology::Computer science | en_US |
| dc.title | Algorithms for various cost criteria in Reinforcement Learning | en_US |
| dc.type | Thesis | en_US |
| dc.degree.name | PhD | en_US |
| dc.degree.level | Doctoral | en_US |
| dc.degree.grantor | Indian Institute of Science | en_US |
| dc.degree.discipline | Engineering | en_US |
