Timezone: »

 
Poster
Interval timing in deep reinforcement learning agents
Ben Deverett · Ryan Faulkner · Meire Fortunato · Gregory Wayne · Joel Leibo

Wed Dec 11 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #151
in Neuroscience and Cognitive Science -- Problem Solving »

The measurement of time is central to intelligent behavior. We know that both animals and artificial agents can successfully use temporal dependencies to select actions. In artificial agents, little work has directly addressed (1) which architectural components are necessary for successful development of this ability, (2) how this timing ability comes to be represented in the units and actions of the agent, and (3) whether the resulting behavior of the system converges on solutions similar to those of biology. Here we studied interval timing abilities in deep reinforcement learning agents trained end-to-end on an interval reproduction paradigm inspired by experimental literature on mechanisms of timing. We characterize the strategies developed by recurrent and feedforward agents, which both succeed at temporal reproduction using distinct mechanisms, some of which bear specific and intriguing similarities to biological systems. These findings advance our understanding of how agents come to represent time, and they highlight the value of experimentally inspired approaches to characterizing agent abilities.

Keywords: Neuroscience · Neuroscience and Cognitive Science · Data, Challenges, Implementations, and Software -> Virtual Environments; Deep Learning · Recurrent Networks; Neuroscience and
[ Paper]  [ Slides] 

Author Information

Ben Deverett (Princeton University)
Ryan Faulkner (Deepmind)
Meire Fortunato (DeepMind)
Gregory Wayne (Google DeepMind)
Joel Leibo (DeepMind)

More from the Same Authors