2018

The Barbados 2018 List of Open Issues in Continual Learning

Schaul, Tom, van Hasselt, Hado, Modayil, Joseph et al.

Understand

We want to make progress toward artificial general intelligence, namely general-purpose agents that autonomously learn how to competently act in complex environments.

  • The purpose of this report is to sketch a research outline, share some of the most important open issues we are facing, and stimulate further discussion in the community.
  • The content is based on some of our discussions during a week-long workshop held in Barbados in February 2018.

Built on

  • A possibility for implementing curiosity and boredom in model-building neural controllers

    J. Schmidhuber · 1991

    Earlier work this paper cites.

  • Continual learning in reinforcement environments

    M. B. Ring · 1994

    Earlier work this paper cites.

  • Predictive representations of state

    M. L. Littman and R. S. Sutton · 2002

    Earlier work this paper cites.

  • Memory retention–the synaptic stability versus plasticity dilemma

    W. C. Abraham and A. Robins · 2005

    Earlier work this paper cites.

  • Horde: A scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction

    R. S. Sutton, J. Modayil, M. Delp, T. Degris, P. M. Pilarski, A. White, and D. Precup · 2011

    Earlier work this paper cites.

  • Scaling-up knowledge for a cognizant robot

    T. Degris and J. Modayil · 2012

    Earlier work this paper cites.

Similar

  • Ella: An efficient lifelong learning algorithm

    P. Ruvolo and E. Eaton · 2013

    Cited alongside, same era.

  • Better Generalization with Forecasts

    T. Schaul and M. B. Ring · 2013

    Cited alongside, same era.

  • Variational information maximisation for intrinsically motivated reinforcement learning

    S. Mohamed and D. J. Rezende · 2015

    Cited alongside, same era.

  • Universal value function approximators

    T. Schaul, D. Horgan, K. Gregor, and D. Silver · 2015

    Cited alongside, same era.

  • Reinforcement learning with unsupervised auxiliary tasks

    Original

    M. Jaderberg, V. Mnih, W. M. Czarnecki, T. Schaul, J. Z. Leibo, D. Silver, and K. Kavukcuoglu · 2016

    Cited alongside, same era.

  • Safe and efficient off-policy reinforcement learning

    R. Munos, T. Stepleton, A. Harutyunyan, and M. Bellemare · 2016

    Cited alongside, same era.

Then

  • A distributional perspective on reinforcement learning

    Original

    M. G. Bellemare, W. Dabney, and R. Munos · 2017

    Later among the works it cites.

  • Multi-objective decision making

    D. M. Roijers and S. Whiteson · 2017

    Later among the works it cites.

  • The predictron: End-to-end learning and planning

    D. Silver, H. van Hasselt, M. Hessel, T. Schaul, A. Guez, T. Harley, G. Dulac-Arnold, D. Reichert, N. Rabinowitz, A. Barreto, and T. Degris · 2017

    Later among the works it cites.

  • Learning to search with mctsnets

    Original

    A. Guez, T. Weber, I. Antonoglou, K. Simonyan, O. Vinyals, D. Wierstra, R. Munos, and D. Silver · 2018

    Closest in time.

  • Reinforcement learning: An introduction

    R. S. Sutton and A. G. Barto · 2018

    Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…