Pseudorehearsal in actor-critic agents with neural network function approximation

Authors

Vladimir Marochko, Innopolis University
Leonard Johard, Innopolis University
Manuel Mazzara, Innopolis University
Luca Longo, Technological University DublinFollow

Author ORCID Identifier

0000-0002-2718-5426

Document Type

Conference Paper

Rights

Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence

Disciplines

Computer Sciences

Publication Details

2018 IEEE 32nd International Conference on Advanced Information Networking and Applications (AINA), 2018, pp. 644-650, doi: 10.1109/AINA.2018.00099.

Abstract

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.

DOI

https://doi.org/10.1109/AINA.2018.00099

Recommended Citation

V. Marochko, L. Johard, M. Mazzara and L. Longo. Pseudorehearsal in Actor-Critic Agents with Neural Network Function Approximation 2018 IEEE 32nd International Conference on Advanced Information Networking and Applications (AINA), 2018, pp. 644-650, doi: 10.1109/AINA.2018.00099.