Peter Stone's Selected Publications

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


Generalizing Curricula for Reinforcement Learning

Sanmit Narvekar and Peter Stone. Generalizing Curricula for Reinforcement Learning. In 4th Lifelong Learning Workshop at the International Conference on Machine Learning (ICML 2020), July 2020.

Download

[PDF]330.4kB  [slides.pdf]3.8MB  

Abstract

Curriculum learning for reinforcement learning (RL) is an active area of research that seeks to speed up training of RL agents on a target task by first training them through a series of progressively more challenging source tasks. Each task in this sequence builds upon skills learned in previous tasks to gradually develop the repertoire needed to solve the final task. Over the past few years, many automated methods to develop curricula have been developed. However, they all have one key limitation: the curriculum must be regenerated from scratch for each new agent or task encountered. In many cases, this generation process can be very expensive. However, there is structure that can be exploited between tasks and agents, such that knowledge gained developing a curriculum for one task can be reused to speed up creating a curriculum for a new task. In this paper, we present a method to generalize a curriculum learned for one set of tasks to a novel set of unseen tasks.

BibTeX Entry

@InProceedings{ICML20-sanmit,
  author = {Sanmit Narvekar and Peter Stone},
  title = {Generalizing Curricula for Reinforcement Learning},
  booktitle = {4th Lifelong Learning Workshop at the International Conference on Machine Learning (ICML 2020)},
  location = {Vienna, Austria},
  month = {July},
  year = {2020},
  abstract = {
        Curriculum learning for reinforcement learning (RL) is an active area of
        research that seeks to speed up training of RL agents on a target task
        by first training them through a series of progressively more
        challenging source tasks. Each task in this sequence builds upon skills
        learned in previous tasks to gradually develop the repertoire needed to
        solve the final task. Over the past few years, many automated methods
        to develop curricula have been developed. However, they all have one
        key limitation: the curriculum must be regenerated from scratch for
        each new agent or task encountered. In many cases, this generation
        process can be very expensive. However, there is structure that can be
        exploited between tasks and agents, such that knowledge gained
        developing a curriculum for one task can be reused to speed up creating
        a curriculum for a new task. In this paper, we present a method to
        generalize a curriculum learned for one set of tasks to a novel set of
        unseen tasks.
  },
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Nov 25, 2020 21:31:01