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

Recent advances in model-free deep reinforcement learning (DRL) show thatsimple model-free methods can be highly effective in challenginghigh-dimensional continuous control tasks. In particular, Truncated QuantileCritics (TQC) achieves state-of-the-art asymptotic training performance on theMuJoCo benchmark with a distributional representation of critics; andRandomized Ensemble Double Q-Learning (REDQ) achieves high sample efficiencythat is competitive with state-of-the-art model-based methods using a highupdate-to-data ratio and target randomization. In this paper, we propose anovel model-free algorithm, Aggressive Q-Learning with Ensembles (AQE), whichimproves the sample-efficiency performance of REDQ and the asymptoticperformance of TQC, thereby providing overall state-of-the-art performanceduring all stages of training. Moreover, AQE is very simple, requiring neitherdistributional representation of critics nor target randomization. Theeffectiveness of AQE is further supported by our extensive experiments,ablations, and theoretical results.

Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance