Learning offline: memory replay in biological and artificial reinforcement learning

Abstract

Learning to act in an environment to maximise rewards is among the brain's key functions. This process has often been conceptualised within the framework of reinforcement learning, which has also gained prominence in machine learning and artificial intelligence (AI) as a way to optimise decision-making. A common aspect of both biological and machine reinforcement learning is the reactivation of previously experienced episodes, referred to as replay. Replay is important for memory consolidation in biological neural networks, and is key to stabilising learning in deep neural networks. Here, we review recent developments concerning the functional roles of replay in the fields of neuroscience and AI. Complementary progress suggests how replay might support learning processes, including generalisation and continual learning, affording opportunities to transfer knowledge across the two fields to advance the understanding of biological and artificial learning and memory.

arXiv commentIn press at Trends in Neurosciences

References in corpus (8)

• Overcoming catastrophic forgetting in neural networks
• Progressive Neural Networks
• Continual Learning Through Synaptic Intelligence
• Hindsight Experience Replay
• Progress & Compress: A scalable framework for continual learning
• Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization
• Continual Learning with Deep Generative Replay
• Revisiting Fundamentals of Experience Replay

Cited by in corpus (2)

• Computational role of sleep in memory reorganization
• Adaptive Intelligence: leveraging insights from adaptive behavior in animals to build flexible AI systems