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.

Stats

• citations35
• S2 citations—
• github stars0
• HF likes0
• heat score11.67
• arxiv keyroscow2021learning

Related papers

• Augmented Replay Memory In Reinforcement Learning With Continuous Control (2019)5.24
• Replay-enhanced Continual Reinforcement Learning (2023)0.00
• Replay For Safety (2021)0.00
• Map-based Experience Replay: A Memory-efficient Solution To Catastrophic Forgetting In Reinforcement Learning (2023)9.23
• Experience Replay For Continual Learning (2018)0.00
• Replay Buffer With Local Forgetting For Adapting To Local Environment Changes In Deep Model-based Reinforcement Learning (2023)0.00
• Generative Memory For Lifelong Reinforcement Learning (2019)0.00
• Prioritized Generative Replay (2024)0.00