Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments release_3falip5y5rh6tnij2nc5upk6gy

by Maruan Al-Shedivat, Trapit Bansal, Yuri Burda, Ilya Sutskever, Igor Mordatch, Pieter Abbeel

Released as a article .

2017  

Abstract

Ability to continuously learn and adapt from limited experience in nonstationary environments is an important milestone on the path towards general intelligence. In this paper, we cast the problem of continuous adaptation into the learning-to-learn framework. We develop a simple gradient-based meta-learning algorithm suitable for adaptation in dynamically changing and adversarial scenarios. Additionally, we design a new multi-agent competitive environment, RoboSumo, and define iterated adaptation games for testing various aspects of continuous adaptation strategies. We demonstrate that meta-learning enables significantly more efficient adaptation than reactive baselines in the few-shot regime. Our experiments with a population of agents that learn and compete suggest that meta-learners are the fittest.
In text/plain format

Archived Files and Locations

application/pdf  2.4 MB
file_b6mhbdxwzjfqnoi6dvmzpv4qrm
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2017-10-10
Version   v1
Language   en ?
arXiv  1710.03641v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 5834743d-4de9-407d-b787-adcb9770f892
API URL: JSON