@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{IJCAI17-Narvekar,
author = {Sanmit Narvekar and Jivko Sinapov and Peter Stone},
title = {Autonomous Task Sequencing for Customized Curriculum Design in Reinforcement Learning},
booktitle = {Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI)},
location = {Melbourne, Australia},
month = {August},
year = {2017},
abstract = {
Transfer learning is a method where an agent reuses knowledge learned in a
source task to improve learning on a target task. Recent work has shown that
transfer learning can be extended to the idea of curriculum learning,
where the agent incrementally accumulates knowledge over a sequence of
tasks (i.e. a curriculum). In most existing work, such curricula have been
constructed manually. Furthermore, they are fixed ahead of time, and do not
adapt to the progress or abilities of the agent. In this paper, we formulate
the design of a curriculum as a Markov Decision Process, which directly
models the accumulation of knowledge as an agent interacts with tasks, and
propose a method that approximates an execution of an optimal policy in this
MDP to produce an agent-specific curriculum. We use our approach to
automatically sequence tasks for 3 agents with varying sensing and action
capabilities in an experimental domain, and show that our method produces
curricula customized for each agent that improve performance relative to
learning from scratch or using a different agent's curriculum.
},
}