Abstract
This paper presents a technique to deal with both discrete and continuous state space systems in POMDPs for reinforcement learning while keeping the state space of an agent compact. First, our computational model for MDP environments, where a concept of "state space filtering" has been introduced and constructed to make properly the state space of an agent smaller by referring to "entropy" calculated based on the state-action mapping, is extended to be applicable in POMDP environments by introducing the mechanism of utilizing effectively of history information. Then, it is possible to deal with a continuous state space as well as a discrete state space. In this, the mechanism of adjusting the amount of history information is also introduced so that the state space of an agent should be compact. Moreover, some computational experiments with a robot navigation problem with a continuous state space have been carried out. The potential and the effectiveness of the extended approach have been confirmed through these experiments
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.