arXiv AI By Mohsen Amiri, Sindri Magn\'usson

Reinforcement Learning in Switching Non-Stationary Markov Decision Processes: Algorithms and Convergence Analysis

Read the original on arXiv AI →

arXiv:2503. 18607v2 Announce Type: replace-cross Abstract: We introduce the Switching Non-Stationary Markov Decision Process (SNS-MDP) framework, in which the environment transitions among a finite set of MDPs governed by a latent Markov chain while the agent observes only the external state.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.