Timezone: »

Continual Reinforcement Learning with Complex Synapses
Christos Kaplanis · Murray Shanahan · Claudia Clopath

Wed Jul 11 09:15 AM -- 12:00 PM (PDT) @ Hall B #26

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 scalar values, an individual synapse in the brain comprises a complex network of interacting biochemical components that evolve at different timescales. In this paper, we show that by equipping tabular and deep reinforcement learning agents with a synaptic model that incorporates this biological complexity (Benna & Fusi, 2016), catastrophic forgetting can be mitigated at multiple timescales. In particular, we find that as well as enabling continual learning across sequential training of two simple tasks, it can also be used to overcome within-task forgetting by reducing the need for an experience replay database.

Author Information

Christos Kaplanis (Imperial College London)

PhD student investigating the topic of continual learning in artificial neural networks.

Murray Shanahan (Imperial College London)
Claudia Clopath (Imperial College London)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors