A canonical theme in neuroscience is that that intelligent behavior relies on multiple memory systems (Tulving, 1985). These will include not only reinforcement-based mechanisms, which allow the value of stimuli and actions to be learned incrementally and through repeated experience, but also instance-based mechanisms, which allow experiences to be encoded rapidly (in “one shot”) in a content-addressable store (Gallistel and King, 2009). The latter form of memory, known as episodic memory (Tulving, 2002), is most often associated with circuits in the medial temporal lobe, prominently including the hippocampus (Squire et al., 2004).
One recent breakthrough in AI has been the successful integration of RL with deep learning (Mnih