go-v.orgdoi

Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari

D V Schmidt, Thomas Schmied · arXiv (Cornell University) · 2021

  • DOI 10.34726/3909
  • Publisher Cornell University
  • Type preprint
  • Issued 2021

Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.

arXiv (Cornell University) · Cornell University · preprint · 2021

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.

Open the resolved locator · 10.34726/3909

Metadata licence: OpenAlex metadata (CC0)

Registry
OpenAlex DOI index + API
Fetched
2026-11-20 18:42 UTC
Cache state
not cached yet (bulk-index+openalex)
Locator
http://arxiv.org/abs/2111.10247
Metadata licence
OpenAlex metadata (CC0)
Scope
Metadata as returned by the resolver; abstracts are never generated here.