English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Since the introduction of DQN, a vast majority of reinforcement learningresearch has focused on reinforcement learning with deep neural networks asfunction approximators. New methods are typically evaluated on a set ofenvironments that have now become standard, such as Atari 2600 games. Whilethese benchmarks help standardize evaluation, their computational cost has theunfortunate side effect of widening the gap between those with ample access tocomputational resources, and those without. In this work we argue that, despitethe community's emphasis on large-scale environments, the traditionalsmall-scale environments can still yield valuable scientific insights and canhelp reduce the barriers to entry for underprivileged communities. Tosubstantiate our claims, we empirically revisit the paper which introduced theRainbow algorithm [Hessel et al., 2018] and present some new insights into thealgorithms used by Rainbow.

Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research