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

Sample efficiency is one of the most critical issues for online reinforcementlearning (RL). Existing methods achieve higher sample efficiency by adoptingmodel-based methods, Q-ensemble, or better exploration mechanisms. We, instead,propose to train an off-policy RL agent via updating on a fixed sampled batchmultiple times, thus reusing these samples and better exploiting them within asingle optimization loop. We name our method sample multiple reuse (SMR). Wetheoretically show the properties of Q-learning with SMR, e.g., convergence.Furthermore, we incorporate SMR with off-the-shelf off-policy RL algorithms andconduct experiments on a variety of continuous control benchmarks. Empiricalresults show that SMR significantly boosts the sample efficiency of the basemethods across most of the evaluated tasks without any hyperparameter tuning oradditional tricks.

Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse