Pseudorehearsal in actor-critic agents

2017/04/17 by Vladimir Marochko, Marochko Vladimir, Vladimir, Marochko +4
Computer Science · Physics and Astronomy · #Adaptive Dynamic Programming Control #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Model Reduction and Neural Networks #Reinforcement Learning in Robotics #cs.AI

paper · pdf · doi:10.48550/arxiv.1704.04912

arxiv created 2017/04/17 · openalex publication_date 2017/04/17 · arxiv updated 2017/04/18 · openalex created_date 2017/04/28 · openalex updated_date 2026/07/28

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.

Citations

• Connectionist models of recognition memory: Constraints imposed by learning and forgetting functions.
• Catastrophic Forgetting, Rehearsal and Pseudorehearsal

Related

• Pseudorehearsal in actor-critic agents with neural network function approximation
• Catastrophic Forgetting, Rehearsal and Pseudorehearsal
• GRIm-RePR: Prioritising Generating Important Features for Pseudo-Rehearsal
• Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks
• Pseudo Rehearsal using non photo-realistic images