Deep Learning Policy Quantization

Wolfshaar, Jos van de; Wiering, Marco A.; Schomaker, Lambert

doi:10.5220/0006592901220130

Search citation statements

Order By: Relevance

Paper Sections

Select...

The Catch Environments1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2021

Publication Types

Select...

Other1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this end, we have implemented four different versions of the Catch game, a simple RL task that was first presented by Mnih et al (2014), and that has been widely used within the literature for investigating the performance of DRL algorithms in a fast, and computationally less expensive manner than the one required by the Atari games (van de Wolfshaar et al, 2018;Aittahar et al, 2020).…”

Section: The Catch Environmentsmentioning

confidence: 99%

On The Transferability of Deep-Q Networks

Sabatelli¹,

Geurts²

2021

Preprint

View full text Add to dashboard Cite

Transfer Learning (TL) is an efficient machine learning paradigm that allows overcoming some of the hurdles that characterize the successful training of deep neural networks, ranging from long training times to the needs of large datasets. While exploiting TL is a well established and successful training practice in Supervised Learning (SL), its applicability in Deep Reinforcement Learning (DRL) is rarer.In this paper, we study the level of transferability of three different variants of Deep-Q Networks on popular DRL benchmarks as well as on a set of novel, carefully designed control tasks. Our results show that transferring neural networks in a DRL context can be particularly challenging and is a process which in most cases results in negative transfer. In the attempt of understanding why Deep-Q Networks transfer so poorly, we gain novel insights into the training dynamics that characterizes this family of algorithms.

show abstract

Section: The Catch Environmentsmentioning

confidence: 99%