@InProceedings{Bee01Lea,
  author    = {Michael Beetz and Thorsten Belker},
  title     = {Learning Structured Reactive Navigation Plans from Executing MDP policies},
  booktitle = {Proceedings of the 5th International Conference on Autonomous Agents},
  pages     = {19--20},
  year      = {2001},
  bib2html_pubtype  = {Refereed Conference Paper},
  bib2html_rescat   = {Robot Learning},
  bib2html_groups   = {IAS},
  bib2html_funding  = {ignore},
  bib2html_keywords = {Robot, Learning},
  abstract = {Autonomous robots, such as robot office couriers, need navigation routines that support flexible
              task execution and effective action planning. This paper describes XfrmLearn, a system that learns
              structured symbolic navigation plans. Given a navigation task, XfrmLearn learns to structure
              continuous navigation behavior and represents the learned structure as compact and transparent
              plans. The structured plans are obtained by starting with monolithic default plans that are
              optimized for average performance and adding subplans to improve the navigation performance for the
              given task. Compactness is achieved by incorporating only subplans that achieve significant
              performance gains. The resulting plans support action planning and opportunistic task execution.
              XfrmLearn is implemented and extensively evaluated on an autonomous mobile robot.}
}