• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Accelerating imitation learning in relational domains via transfer by initialization
 
  • Details
  • Full
Options
2014
Conference Paper
Title

Accelerating imitation learning in relational domains via transfer by initialization

Abstract
The problem of learning to mimic a human expert/teacher from training trajectories is called imitation learning. Tomake the process of teaching easier in this setting, we propose to employ transfer learning (where one learns on a source problem and transfers the knowledge to potentially more complex target problems). We consider multi-relational environments such as real-time strategy games and use functional-gradient boosting to capture and transfer the models learned in these environments. Our experiments demonstrate that our learner learns a very good initial model from the simple scenario and effectively transfers the knowledge to the more complex scenario thus achieving a jump start, a steeper learning curve and a higher convergence in performance.
Author(s)
Natarajan, S.
Odom, P.
Joshi, S.
Khot, T.
Kersting, Kristian  
Tadepalli, P.
Mainwork
Inductive logic programming. 23rd International Conference, ILP 2013  
Conference
International Conference on Inductive Logic Programming (ILP) 2013  
DOI
10.1007/978-3-662-44923-3_5
Language
English
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024