no code implementations • 27 Nov 2019 • Craig Atkinson, Brendan McCane, Lech Szymanski, Anthony Robins
Pseudo-rehearsal allows neural networks to learn a sequence of tasks without forgetting how to perform in earlier tasks.
1 code implementation • 6 Dec 2018 • Craig Atkinson, Brendan McCane, Lech Szymanski, Anthony Robins
We propose a model that overcomes catastrophic forgetting in sequential reinforcement learning by combining ideas from continual learning in both the image classification domain and the reinforcement learning domain.
no code implementations • 12 Feb 2018 • Craig Atkinson, Brendan McCane, Lech Szymanski, Anthony Robins
In general, neural networks are not currently capable of learning tasks in a sequential fashion.