Bayesian $\kappa$-Explorer for Minimax Model Estimation in MDPs
Computer Science > Machine Learning [Submitted on 18 Nov 2026] Title:Bayesian $κ$-Explorer for Minimax Model Estim
📌 核心要点
- Computer Science > Machine Learning
- [Submitted on 18 Nov 2026]
- Title:Bayesian $κ$-Explorer for Minimax Model Estimation in MDPs
Computer Science > Machine Learning
[Submitted on 18 Nov 2026]
Title:Bayesian $κ$-Explorer for Minimax Model Estimation in MDPs
View PDF HTML (experimental)Abstract:We study active exploration for minimax transition estimation in unknown Markov decision processes (MDPs). Frequentist $\kappa$-Explorer~\citep{gu2026kappa} addresses this problem through a parameterized family of exploration objectives, but requires confidence-bound constructions and joint optimization over plausible transition kernels and occupancy measures, introducing a computational burden that limits its practical applicability. We develop Bayesian $\kappa$-Explorer, which simplifies this procedure by placing Dirichlet priors on the transition distributions. Under the posterior mean estimator, the posterior expected squared $\ell_2$ error equals the total posterior variance, providing a closed-form exploration signal. The algorithm plans under the posterior mean model, eliminating confidence-set optimization. Under the stated assumptions, this simpler planning procedure retains the $\widetilde{O}(T^{-1/3})$ surrogate convergence rate of frequentist $\kappa$-Explorer. We further bound the maximum posterior variance relative to the optimal asymptotic minimax allocation benchmark. Experiments on Pendulum, Mountain Car, and Taxi demonstrate lower worst-case transition-estimation errors than the tested baselines.
Additional Features
References & Citations
Loading...
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Connected Papers (What is Connected Papers?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv (What is alphaXiv?)
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Hugging Face (What is Huggingface?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
CORE Recommender (What is CORE?)
IArxiv Recommender
(What is IArxiv?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.