English

Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer

Machine Learning 2023-02-21 v1

Abstract

In this paper, we study the problem of transferring the available Markov Decision Process (MDP) models to learn and plan efficiently in an unknown but similar MDP. We refer to it as \textit{Model Transfer Reinforcement Learning (MTRL)} problem. First, we formulate MTRL for discrete MDPs and Linear Quadratic Regulators (LQRs) with continuous state actions. Then, we propose a generic two-stage algorithm, MLEMTRL, to address the MTRL problem in discrete and continuous settings. In the first stage, MLEMTRL uses a \textit{constrained Maximum Likelihood Estimation (MLE)}-based approach to estimate the target MDP model using a set of known MDP models. In the second stage, using the estimated target MDP model, MLEMTRL deploys a model-based planning algorithm appropriate for the MDP class. Theoretically, we prove worst-case regret bounds for MLEMTRL both in realisable and non-realisable settings. We empirically demonstrate that MLEMTRL allows faster learning in new MDPs than learning from scratch and achieves near-optimal performance depending on the similarity of the available MDPs and the target MDP.

Keywords

Cite

@article{arxiv.2302.09273,
  title  = {Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer},
  author = {Hannes Eriksson and Debabrota Basu and Tommy Tram and Mina Alibeigi and Christos Dimitrakakis},
  journal= {arXiv preprint arXiv:2302.09273},
  year   = {2023}
}

Comments

27 pages, 7 figures

R2 v1 2026-06-28T08:43:23.048Z