Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Task Factorization in Curriculum Learning

Task Factorization in Curriculum Learning.
Reuth Mirsky, Shahaf S. Shperberg, Yulin Zhang, Zifan Xu, Yuqian Jiang, Jiaxun Cui, and Peter Stone.
In ICML workshop on Decision Awareness in Reinforcement Learning (DARL), July 2022.
recorded presentation

Download

[PDF]1011.6kB  

Abstract

A common challenge for learning when applied to a complex ``target'' task is that learning that task all at once can be too difficult due to inefficient exploration given a sparse reward signal. Curriculum Learning addresses this challenge by sequencing training tasks for a learner to facilitate gradual learning. One of the crucial steps in finding a suitable curriculum learning approach is to understand the dimensions along which the domain can be factorized. In this paper, we identify different types of factorizations common in the literature of curriculum learning for reinforcement learning tasks: factorizations that involve the agent, the environment, or the mission. For each factorization category, we identify the relevant algorithms and techniques that leverage that factorization and present several case studies to showcase how leveraging an appropriate factorization can boost learning using a simple curriculum.

BibTeX Entry

@InProceedings{DARL22-REUTH,
  author = {Reuth Mirsky and Shahaf S. Shperberg and Yulin Zhang and Zifan Xu and Yuqian Jiang and Jiaxun Cui and Peter Stone},
  title = {Task Factorization in Curriculum Learning},
  booktitle = {ICML workshop on Decision Awareness in Reinforcement Learning (DARL)},
  location = {Baltimore, Maryland, USA},
  month = {July},
  year = {2022},
  abstract = {  
A common challenge for learning when applied to a complex ``target'' task is 
that learning that task all at once can be too difficult due to inefficient 
exploration given a sparse reward signal.  Curriculum Learning addresses this
 challenge by sequencing training tasks for a learner to facilitate gradual
 learning. One of the crucial steps in finding a suitable curriculum learning
 approach is to understand the dimensions along which the domain can be
 factorized. In this paper, we identify different types of factorizations
 common in the literature of curriculum learning for reinforcement learning
 tasks: factorizations that involve the agent, the environment, or the
 mission. For each factorization category, we identify the relevant algorithms
 and techniques that leverage that factorization and present several case
 studies to showcase how leveraging an appropriate factorization can boost
 learning using a simple curriculum. 
  },
  wwwnote={<a href="https://slideslive.com/38987380">recorded presentation</a>},
}

Generated by bib2html.pl (written by Patrick Riley ) on Mon Mar 25, 2024 00:05:18