Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Learning and Reasoning for Robot Dialog and Navigation Tasks

Keting Lu, Shiqi Zhang, Peter Stone, and Xiaoping Chen. Learning and Reasoning for Robot Dialog and Navigation Tasks. In Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 107–117, Association for Computational Linguistics, 1st virtual meeting, July 2020.
Official version from ACL Digital Library, including a link to the conference presentation

Download

[PDF]3.6MB  

Abstract

Reinforcement learning and probabilistic reasoning algorithms aim at learning from interaction experiences and reasoning with probabilistic contextual knowledge respectively. In this research, we develop algorithms for robot task completions, while looking into the complementary strengths of reinforcement learning and probabilistic reasoning techniques. The robots learn from trial-and-error experiences to augment their declarative knowledge base, and the augmented knowledge can be used for speeding up the learning process in potentially different tasks. We have implemented and evaluated the developed algorithms using mobile robots conducting dialog and navigation tasks. From the results, we see that our robot's performance can be improved by both reasoning with human knowledge and learning from task-completion experience. More interestingly, the robot was able to learn from navigation tasks to improve its dialog strategies.

BibTeX Entry

@InProceedings{SIGDIAL20,
  author = {Keting Lu and Shiqi Zhang and Peter Stone and Xiaoping Chen},
  title     = {Learning and Reasoning for Robot Dialog and Navigation Tasks},
  booktitle      = {Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue},
  month          = {July},
  year           = {2020},
  address        = {1st virtual meeting},
  publisher      = {Association for Computational Linguistics},
  pages     = {107--117},
  abstract  = {Reinforcement learning and probabilistic reasoning
               algorithms aim at learning from interaction experiences
               and reasoning with probabilistic contextual knowledge
               respectively. In this research, we develop algorithms for
               robot task completions, while looking into the
               complementary strengths of reinforcement learning and
               probabilistic reasoning techniques. The robots learn from
               trial-and-error experiences to augment their declarative
               knowledge base, and the augmented knowledge can be used
               for speeding up the learning process in potentially
               different tasks. We have implemented and evaluated the
               developed algorithms using mobile robots conducting
               dialog and navigation tasks. From the results, we see
               that our robot's performance can be improved by both
               reasoning with human knowledge and learning from
               task-completion experience. More interestingly, the robot
               was able to learn from navigation tasks to improve its
               dialog strategies.}, 
  wwwnote={Official version from <a href="https://www.aclweb.org/anthology/2020.sigdial-1.14/">ACL Digital Library</a>, including a link to the conference presentation},
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Nov 25, 2020 21:30:59