@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.90
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@article{RAL20-pavse,
  author = {Brahma Pavse and Faraz Torabi and Josiah Hanna and Garrett Warnell and Peter Stone},
  title = {RIDM: Reinforced Inverse Dynamics Modeling for Learning from a Single Observed Demonstration},
  Journal = {{IEEE} Robotics and Automation Letters (RA-L)},
  wwwnote={Presented at International Conference on Intelligent Robots and Systems ({IROS})\\
   A preliminary version was presented at the <i>Imitation, Intent, and Interaction</i> (I3) Workshop at ICML 2019},
  year = {2020},
  month = {October},
  volume= {5}, issue={4},
  pages="6262--69",
  issn="2377-3766",
  doi="10.1109/LRA.2020.3010750",
  wwwnote={<a href="https://sites.google.com/view/ridm-reinforced-inverse-dynami">Video of the experiments</a>; <a href="https://www.youtube.com/watch?v=QDReBWEoDtE">13-minute video presentation</a>.},
  abstract = {
Augmenting reinforcement learning with imitation learning is often hailed as a 
method by which to improve upon learning from scratch. However, most existing 
methods for integrating these two techniques are subject to several strong 
assumptions---chief among them that information about demonstrator actions is 
available. In this paper, we investigate the extent to which this assumption 
is necessary by introducing and evaluating reinforced inverse dynamics 
modeling (RIDM), a novel paradigm for combining imitation from observation 
(IfO) and reinforcement learning with no dependence on demonstrator action 
information. Moreover, RIDM requires only a single demonstration trajectory 
and is able to operate directly on raw (unaugmented) state features. We find 
experimentally that RIDM performs favorably compared to a baseline approach 
for several tasks in simulation as well as for tasks on a real UR5 robot arm. 
Experiment videos can be found at 
https://sites.google.com/view/ridm-reinforced-inverse-dynami.
  },
}