Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
Maruan Al-Shedivat
and
Trapit Bansal
and
Yuri Burda
and
Ilya Sutskever
and
Igor Mordatch
and
Pieter Abbeel
arXiv e-Print archive - 2017 via Local arXiv
Keywords:
cs.LG, cs.AI
First published: 2017/10/10 (7 years ago) 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.