Near-Optimal Learning and Planning in Separated Latent MDPs
Name
chen-fanchen-sm-eecs-2025-thesis.pdf
Description
Thesis PDF
Size
987.57 KB
Format
Adobe PDF
Checksum (MD5)
2a95fd56fd642ead7cd9950ef0502823
Author(s)
Chen, Fan
Advisor(s)
Daskalakis, Constantinos
Rakhlin, Alexander
Date Issued
February 2025
Publisher
Massachusetts Institute of Technology
Abstract
We study computational and statistical aspects of learning Latent Markov Decision Processes (LMDPs). In this model, the learner interacts with an MDP drawn at the beginning of each epoch from an unknown mixture of MDPs. To sidestep known impossibility results, we consider several notions of δ-separation of the constituent MDPs. The main thrust of this paper is in establishing a nearly-sharp statistical threshold for the horizon length necessary for efficient learning. On the computational side, we show that under a weaker assumption of separability under the optimal policy, there is a quasi-polynomial algorithm with time complexity scaling in terms of the statistical threshold. We further show a near-matching time complexity lower bound under the exponential time hypothesis.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
