Parseval Regularization for Continual Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chung, Wesley, Cherif, Lynn, Meger, David, Precup, Doina
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916515397238784
author Chung, Wesley
Cherif, Lynn
Meger, David
Precup, Doina
author_facet Chung, Wesley
Cherif, Lynn
Meger, David
Precup, Doina
contents Loss of plasticity, trainability loss, and primacy bias have been identified as issues arising when training deep neural networks on sequences of tasks -- all referring to the increased difficulty in training on new tasks. We propose to use Parseval regularization, which maintains orthogonality of weight matrices, to preserve useful optimization properties and improve training in a continual reinforcement learning setting. We show that it provides significant benefits to RL agents on a suite of gridworld, CARL and MetaWorld tasks. We conduct comprehensive ablations to identify the source of its benefits and investigate the effect of certain metrics associated to network trainability including weight matrix rank, weight norms and policy entropy.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07224
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Parseval Regularization for Continual Reinforcement Learning
Chung, Wesley
Cherif, Lynn
Meger, David
Precup, Doina
Machine Learning
Artificial Intelligence
Loss of plasticity, trainability loss, and primacy bias have been identified as issues arising when training deep neural networks on sequences of tasks -- all referring to the increased difficulty in training on new tasks. We propose to use Parseval regularization, which maintains orthogonality of weight matrices, to preserve useful optimization properties and improve training in a continual reinforcement learning setting. We show that it provides significant benefits to RL agents on a suite of gridworld, CARL and MetaWorld tasks. We conduct comprehensive ablations to identify the source of its benefits and investigate the effect of certain metrics associated to network trainability including weight matrix rank, weight norms and policy entropy.
title Parseval Regularization for Continual Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2412.07224