Start Date

19-5-2023 11:40 AM

End Date

19-5-2023 12:00 PM

Document Type

Full Paper

Keywords

Place Cells, Hippocampal Replay, Reinforcement Learning, Actor-Critic, Latent Learning

Description

In the last decade, studies have demonstrated that hippocampal place cells influence rats’ navigational learning ability. Moreover, researchers have observed that place cell sequences associated with routes leading to a reward are reactivated during rest periods. This phenomenon is known as Hippocampal Replay, which is thought to aid navigational learning and memory consolidation. These findings in neuroscience have inspired new robot navigation models that emulate the learning process of mammals. This study presents a novel model that encodes path information using place cell connections formed during online navigation. Our model employs these connections to generate sequences of
state-action pairs to train our actor-critic reinforcement learning model offline. Our results indicate that our method can accelerate the learning process of solving an open-world navigational task. Specifically, we demonstrate that our approach can learn optimal paths through open-field mazes with obstacles.

DOI

https://doi.org/10.5038/LZSJ6129

Included in

Robotics Commons

Share

COinS
 
May 19th, 11:40 AM May 19th, 12:00 PM

Reinforcement Learning and Place Cell Replay in Spatial Navigation

In the last decade, studies have demonstrated that hippocampal place cells influence rats’ navigational learning ability. Moreover, researchers have observed that place cell sequences associated with routes leading to a reward are reactivated during rest periods. This phenomenon is known as Hippocampal Replay, which is thought to aid navigational learning and memory consolidation. These findings in neuroscience have inspired new robot navigation models that emulate the learning process of mammals. This study presents a novel model that encodes path information using place cell connections formed during online navigation. Our model employs these connections to generate sequences of
state-action pairs to train our actor-critic reinforcement learning model offline. Our results indicate that our method can accelerate the learning process of solving an open-world navigational task. Specifically, we demonstrate that our approach can learn optimal paths through open-field mazes with obstacles.