Continual Reinforcement Learning with Complex Synapses
ICML, pp. 2497-2506, 2018.
Unlike humans, who are capable of continual learning over their lifetimes, artificial neural networks have long been known to suffer from a phenomenon known as catastrophic forgetting, whereby new learning can lead to abrupt erasure of previously acquired knowledge. Whereas in a neural network the parameters are typically modelled as scal...More
PPT (Upload PPT)