English

Pseudorehearsal in actor-critic agents

Artificial Intelligence 2017-04-18 v1

Abstract

Catastrophic forgetting has a serious impact in reinforcement learning, as the data distribution is generally sparse and non-stationary over time. The purpose of this study is to investigate whether pseudorehearsal can increase performance of an actor-critic agent with neural-network based policy selection and function approximation in a pole balancing task and compare different pseudorehearsal approaches. We expect that pseudorehearsal assists learning even in such very simple problems, given proper initialization of the rehearsal parameters.

Keywords

Cite

@article{arxiv.1704.04912,
  title  = {Pseudorehearsal in actor-critic agents},
  author = {Marochko Vladimir and Leonard Johard and Manuel Mazzara},
  journal= {arXiv preprint arXiv:1704.04912},
  year   = {2017}
}
R2 v1 2026-06-22T19:18:56.358Z