TY - GEN AU - Matthew Botvinick AU - Sam Ritter AU - Jane X. Wang AU - Zeb Kurth-Nelson AU - Charles Blundell AU - Demis Hassabis TI - Reinforcement Learning, Fast and Slow PY - 2019/// CY - [Place of publication not identified] PB - Elsevier BV KW - deep reinforcement learning KW - sample efficiency KW - human learning KW - fast learning KW - incremental learning KW - learning speed KW - B. Sc. Artificial Intelligence KW - UMUN open access collection KW - reinforcement learning KW - Review articles N1 - Publication type: Review article; Linked open-access copy: published version; Open access; no subscription required for the linked open-access version N2 - Deep reinforcement learning (RL) methods have driven impressive advances in artificial intelligence in recent years, exceeding human performance in domains ranging from Atari to Go to no-limit poker. This progress has drawn the attention of cognitive scientists interested in understanding human learning. However, the concern has been raised that deep RL may be too sample-inefficient - that is, it may simply be too slow - to provide a plausible model of how humans learn. In the present review, we counter this critique by describing recently developed techniques that allow deep RL to operate more nimbly, solving problems much more quickly than previous methods. Although these techniques were developed in an AI context, we propose that they may have rich implications for psychology and neuroscience. A key insight, arising from these AI methods, concerns the fundamental connection between fast RL and slower, more incremental forms of learning UR - http://www.cell.com/article/S1364661319300610/pdf ER -