Partially Observable Markov Decision Processes With Reward Information: Basic Ideas and Models

Xi-Ren Cao, Xianping Guo
<span title="">2007</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="" style="color: black;">IEEE Transactions on Automatic Control</a> </i> &nbsp;
In a partially observable Markov decision process (POMDP), if the reward can be observed at each step, then the observed reward history contains information on the unknown state. This information, in addition to the information contained in the observation history, can be used to update the state probability distribution. The policy thus obtained is called a reward-information policy (RI-policy); an optimal RI-policy performs no worse than any normal optimal policy depending only on the
more &raquo; ... ion history. The above observation leads to four different problem-formulations for POMDPs depending on whether the reward function is known and whether the reward at each step is observable. This exploratory work may attract attention to these interesting problems. Index Terms-Partially observable Markov decision process (POMDP), reward-information policy.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="">doi:10.1109/tac.2007.894520</a> <a target="_blank" rel="external noopener" href="">fatcat:eqscs76qpvhndcdsirro66qcxi</a> </span>
<a target="_blank" rel="noopener" href="" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href=""> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> </button> </a>