Continual Reinforcement Learning With Complex Synapses

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykaplanis2018continual

Related papers

• Experience Replay For Continual Learning (2018)0.00
• Reducing Catastrophic Forgetting When Evolving Neural Networks (2019)0.00
• Replay-enhanced Continual Reinforcement Learning (2023)0.00
• Self-activating Neural Ensembles For Continual Reinforcement Learning (2022)0.00
• Augmented Replay Memory In Reinforcement Learning With Continuous Control (2019)5.24
• Continual Learning Using World Models For Pseudo-rehearsal (2019)0.00
• Learning Fast Changing Slow In Spiking Neural Networks (2024)3.58
• Replay Buffer With Local Forgetting For Adapting To Local Environment Changes In Deep Model-based Reinforcement Learning (2023)0.00