Vladimir Marochko,Leonard Johard,Manuel Mazzara,Luca Longo
Abstract URL: http://arxiv.org/abs/1712.07686v2
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.