Learning Probabilistic Relational Dynamics for Multiple Tasks

Authors Ashwin Deshpande, Brian Milch, Luke S. Zettlemoyer, Leslie Pack Kaelbling

Thumbnail PDF


  • Filesize: 211 kB
  • 10 pages

Document Identifiers

Author Details

Ashwin Deshpande
Brian Milch
Luke S. Zettlemoyer
Leslie Pack Kaelbling

Cite AsGet BibTex

Ashwin Deshpande, Brian Milch, Luke S. Zettlemoyer, and Leslie Pack Kaelbling. Learning Probabilistic Relational Dynamics for Multiple Tasks. In Probabilistic, Logical and Relational Learning - A Further Synthesis. Dagstuhl Seminar Proceedings, Volume 7161, pp. 1-10, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)


The ways in which an agent's actions affect the world can often be modeled compactly using a set of relational probabilistic planning rules. This extended abstract addresses the problem of learning such rule sets for multiple related tasks. We take a hierarchical Bayesian approach, in which the system learns a prior distribution over rule sets. We present a class of prior distributions parameterized by a rule set prototype that is stochastically modified to produce a task-specific rule set. We also describe a coordinate ascent algorithm that iteratively optimizes the task-specific rule sets and the prior distribution. Experiments using this algorithm show that transferring information from related tasks significantly reduces the amount of training data required to predict action effects in blocks-world domains.
  • Hierarchical Bayesian models
  • transfer learning
  • multi-task learning
  • probabilistic planning rules


  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    PDF Downloads
Questions / Remarks / Feedback

Feedback for Dagstuhl Publishing

Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail