Policy space identification in configurable environments

DOI10.1007/S10994-021-06033-3MaRDI QIDQ2163245zbMATH OpenOpenAlexFDO

Authors Alberto Maria Metelli, Guglielmo Manneschi, Marcello Restelli

Publication date 10 August 2022

Published in Machine Learning (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/1909.03984

zbMATH Keywords

configurable Markov decision processeslikelihood ratio testpolicy space identificationreinforcement learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Identification of optimal policies in Markov decision processes
• Stochastic policy design in a learning environment with rational expectations.
• Interactive policy learning through confidence-based autonomy
• k-Certainty Exploration Method: an action selector to identify the environment in reinforcement learning
• Policy iterations for reinforcement learning problems in continuous time and space -- fundamental theory and methods

Cites work

• A tail inequality for quadratic forms of subgaussian random vectors
• Concentration inequalities. A nonasymptotic theory of independence
• Finite-sample analysis of least-squares policy iteration
• Generalized inverses. Theory and applications.
• scientific article; zbMATH DE number 3146392 (Why is no real title available?)
• scientific article; zbMATH DE number 3173999 (Why is no real title available?)
• scientific article; zbMATH DE number 44577 (Why is no real title available?)
• scientific article; zbMATH DE number 46578 (Why is no real title available?)
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• Identification in Parametric Models
• Importance sampling techniques for policy optimization
• Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path
• Nonasymptotic sequential tests for overlapping hypotheses applied to near-optimal arm identification in bandit models
• Rates of convergence for empirical processes of stationary mixing sequences
• Reinforcement learning. An introduction
• The Large-Sample Distribution of the Likelihood Ratio for Testing Composite Hypotheses
• The philosophy of Bayes factors and the quantification of statistical evidence

Describes a project that uses

Uses Software

• SBEED
• PILCO
• SQIL

This page was built for publication: Policy space identification in configurable environments

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2163245)