arxivst stuff from arxiv that you should probably bookmark

Pseudorehearsal in actor-critic agents

Abstract · Apr 17, 2017 09:27 ·

pseudorehearsal agent forgetting critic actor policy reward action cs-ai

Arxiv Abstract

  • Marochko Vladimir
  • Leonard Johard
  • Manuel Mazzara

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.

Read the paper (pdf) »