@COMMENT This file was generated by bib2html.pl version 0.90
@COMMENT written by Patrick Riley
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InProceedings{IROS2021-torabi,
author = {Faraz Torabi and Garrett Warnell and Peter Stone},
title = {DEALIO: Data-Efficient Adversarial Learning for Imitation from Observation},
booktitle = {Proceedings of The IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
location = {Prague, Czech Republic},
month = {September},
year = {2021},
abstract = {
In imitation learning from observation (IfO), a learning agent seeks to imitate
a demonstrating agent using only observations of the demonstrated behavior
without access to the control signals generated by the demonstrator. Recent
methods based on adversarial imitation learning have led to state-of-the-art
performance on IfO problems, but they typically suffer from high sample
complexity due to a reliance on data-inefficient, model-free reinforcement
learning algorithms. This issue makes them impractical to deploy in real-world
settings, where gathering samples can incur high costs in terms of time,
energy, and risk. In this work, we hypothesize that we can incorporate ideas
from model-based reinforcement learning with adversarial methods for IfO in
order to increase the data efficiency of these methods without sacrificing
performance. Specifically, we consider time-varying linear Gaussian policies,
and propose a method that integrates the linear-quadratic regulator with path
integral policy improvement into an existing adversarial IfO framework. The
result is a more data-efficient IfO algorithm with better performance, which
we show empirically in four simulation domains: using far fewer interactions
with the environment, the proposed method exhibits similar or better
performance than the existing technique.
},
wwwnote = {Video presentation}
}