Pseudorehearsal in actor-critic agents with neural network function approximation

12/20/2017

∙

by   Vladimir Marochko, et al.

∙

0

∙

share

Catastrophic forgetting has a significant negative impact in reinforcement learning. The purpose of this study is to investigate how pseudorehearsal can change performance of an actor-critic agent with neural-network function approximation. We tested agent in a pole balancing task and compared different pseudorehearsal approaches. We have found that pseudorehearsal can assist learning and decrease forgetting.