<?xml version="1.0" encoding="utf-8"?>
<?xml-stylesheet type="text/xsl" href="style/detail_T.xsl"?>
<bibitem type="L4">   <ARLID>0646408</ARLID> <utime>20260304131628.0</utime><mtime>20260223235959.9</mtime>         <title language="eng" primary="1">Robust Sequential Decision-Making in Adversarial Environments: Codebase</title>  <publisher> <pub_time>2025</pub_time> </publisher>    <keyword>Dynamic programming</keyword>   <keyword>adversarial machine learning (AdvML)</keyword>   <keyword>Multi-agent reinforcement learning (MARL)</keyword>   <keyword>robust reinforcement learning</keyword>   <keyword>Bayesian reinforcement learning</keyword>    <author primary="1"> <ARLID>cav_un_auth*0491463</ARLID> <name1>Ružejnikov</name1> <name2>Jurij</name2> <institution>UTIA-B</institution> <full_dept language="cz">Adaptivní systémy</full_dept> <full_dept language="eng">Department of Adaptive Systems</full_dept> <department language="cz">AS</department> <department language="eng">AS</department> <country>CZ</country>  <share>100</share> <garant>K</garant> <fullinstit>Ústav teorie informace a automatizace AV ČR, v. v. i.</fullinstit> </author>   <source> <source_type>online databáze</source_type> <source_size>90.89 kB</source_size> <url>https://doi.org/10.6084/m9.figshare.30788984</url>  </source>        <cas_special> <project> <project_id>101168272</project_id> <agency>EC</agency> <country>XE</country>   <ARLID>cav_un_auth*0492513</ARLID> </project> <project> <project_id>CA24136</project_id> <agency>EC</agency> <country>XE</country>  <ARLID>cav_un_auth*0504278</ARLID> </project> <project> <project_id>2025A1013</project_id> <agency>Provozně Ekonomická Fakulta ČZU</agency> <country>CZ</country> <ARLID>cav_un_auth*0504279</ARLID> </project>  <abstract language="eng" primary="1">This repository contains experimental datasets, results and configuration files supporting the research article „Robust Sequential Decision-Making in Adversarial Environments“. The associated study addresses reinforcement learning in non-stationary, adversarial environments where standard Markov Decision Process (MDP) assumptions are violated, introducing a model-based framework for Threatened Markov Decision Process (TMDP) that utilises Bayesian belief updates to compute robust policies.</abstract>     <RIV>IN</RIV> <FORD0>10000</FORD0> <FORD1>10100</FORD1> <FORD2>10102</FORD2>    <reportyear>2026</reportyear>       <num_of_auth>1</num_of_auth>  <inst_support> RVO:67985556 </inst_support>  <permalink>https://hdl.handle.net/11104/0376313</permalink>  <cooperation> <ARLID>cav_un_auth*0478849</ARLID> <name>Provozně ekonomická fakulta, Česká zemědělská univerzita v Praze</name> <institution>PEF CZU</institution> <country>CZ</country> </cooperation>  <confidential>S</confidential>         <arlyear>2025</arlyear>       <unknown tag="mrcbU10"> 2025 </unknown> </cas_special> </bibitem>