TY  - BOOK
AU  - Guin, Soumyajit
AU  - Advised by Bhatnagar, Shalabh
TI  - Algorithms for various cost criteria in reinforcement learning
U1  - 006.31 
PY  - 2025///
CY  - Bangalore : 
PB  - Indian Institute of Science
KW  - Reinforcement Learning
KW  - Algorithms	
KW  - Finite Horizon	
KW  - Risk-Sensitive Cost	
KW  - Discounted Cost	
KW  - Critic-Actor Algorithm	
KW  - Convergence	
N1  - Includes bibliographical references; PhD;2025;Computer Science and Automation
N2  - 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.	
UR  - https://etd.iisc.ac.in/handle/2005/6892
ER  -