Machine Learning

Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments

Tagged: 

This topic contains 0 replies, has 1 voice, and was last updated by  arXiv 2 months, 1 week ago.


  • arXiv
    5 pts

    Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments

    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.

    Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
    by Maruan Al-Shedivat, Trapit Bansal, Yuri Burda, Ilya Sutskever, Igor Mordatch, Pieter Abbeel
    https://arxiv.org/pdf/1710.03641v1.pdf

You must be logged in to reply to this topic.