Reinforcement Learning, Fast and Slow

doi:10.1016/j.tics.2019.02.006

Reinforcement Learning, Fast and Slow

2019-05-01

377

OA

AI

DOI：10.1016/j.tics.2019.02.006

Original

Save

View PDF

Abstract

En 中文

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.

Keywords:

PREFRONTAL CORTEX

NEURAL-NETWORKS

MODEL

PREDICTION

SYSTEMS

REWARD

DOPAMINE

MEMORY

BRAIN

GO

Reinforcement Learning, Fast and Slow

Abstract

AI Summary

Journal

Organization