<ul><li>Researchers integrate a computational neuroscience model of scale invariant memory into deep reinforcement learning (RL) agents.</li><li>Agents built with scale invariant memory can learn robustly across a wide range of temporal scales, unlike agents built with commonly used recurrent memory architectures such as LSTM.</li><li>This integration of computational principles from neuroscience and cognitive science enhances adaptability to complex temporal dynamics in deep neural networks.</li><li>The result mirrors some of the core properties of human learning.</li></ul>

Deep reinforcement learning with time-scale invariant memory

Discover more