<div class="csl-bib-body">
<div class="csl-entry">Schmidt, D., & Schmied, T. (2021, December 13). <i>Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari</i> [Poster Presentation]. Deep RL Workshop NeurIPS 2021, Online, Unknown. https://doi.org/10.34726/3909</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/176002
-
dc.identifier.uri
https://doi.org/10.34726/3909
-
dc.description.abstract
Across the Arcade Learning Environment, Rainbow achieves a level of performance competitive with humans and modern RL algorithms. However, attaining this level of performance requires large amounts of data and hardware resources, making research in this area computationally expensive and use in practical applications often infeasible. This paper's contribution is threefold: We (1) propose an improved version of Rainbow, seeking to drastically reduce Rainbow's data, training time, and compute requirements while maintaining its competitive performance; (2) we empirically demonstrate the effectiveness of our approach through experiments on the Arcade Learning Environment, and (3) we conduct a number of ablation studies to investigate the effect of the individual proposed modifications. Our improved version of Rainbow reaches a median human normalized score close to classic Rainbow's, while using 20 times less data and requiring only 7.5 hours of training time on a single GPU. We also provide our full implementation including pre-trained models.
en
dc.language.iso
en
-
dc.relation.hasversion
https://doi.org/10.48550/arXiv.2111.10247
-
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
-
dc.subject
Machine Learning
en
dc.title
Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari
