@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{ICAPS23-bajaj,
author = {Vaibhav Bajaj and Guni Sharon and Peter Stone},
title = {Task Phasing: Automated Curriculum Learning from Demonstrations},
booktitle = {Proceedings of the 33rd International Conference on Automated Planning and Scheduling (ICAPS 2023)},
location = {Prague, Czech Republic},
month = {July},
year = {2023},
abstract = {
Applying reinforcement learning (RL) to sparse reward
domains is notoriously challenging due to insufficient
guiding signals. Common RL techniques for addressing
such domains include (1) learning from demonstrations
and (2) curriculum learning. While these two approaches
have been studied in detail, they have rarely been
considered together. This paper aims to do so by
introducing a principled task phasing approach that uses
demonstrations to automatically generate a curriculum
sequence. Using inverse RL from (subopti- mal)
demonstrations we define a simple initial task. Our task
phasing approach then provides a framework to gradually
increase the complexity of the task all the way to the
target task, while retuning the RL agent in each phasing
iteration. Two approaches for phasing are considered:
(1) gradually increasing the proportion of time steps an
RL agent is in control, and (2) phasing out a guiding
informative reward function. We present conditions that
guarantee the convergence of these approaches to an
optimal policy. Experimental results on 3 sparse reward
domains demonstrate that our task phasing approaches
outperform state-of-the-art approaches with respect to
asymptotic performance.
},
wwwnote={Accompanying code},
}