3 papers
cs.LG2026
Near-Optimal Sample Complexity for Recursive Entropic Risk Reinforcement Learning with a Generative Model
Amirparsa Bahrami, Oliver Mortensen, Mohammad Sadegh Talebi
In this paper, we study the sample complexities of value and policy learning in finite discounted Markov decision processes (MDPs) under recursive entropic risk preferences with ri…
cs.LG2026
On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents
Oliver Mortensen, Mohammad Sadegh Talebi
We study risk-sensitive reinforcement learning in finite discounted MDPs, where a generative model of the MDP is assumed to be available. We consider a family or risk measures call…
cs.LG2025
Recursive Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative Model
Oliver Mortensen, Mohammad Sadegh Talebi
We study risk-sensitive reinforcement learning in finite discounted MDPs with recursive entropic risk measures (ERM), where the risk parameter controls the agent's risk a…