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

In this paper we address the problem of learning and backtesting inventorycontrol policies in the presence of general arrival dynamics -- which we termas a quantity-over-time arrivals model (QOT). We also allow for orderquantities to be modified as a post-processing step to meet vendor constraintssuch as order minimum and batch size constraints -- a common practice in realsupply chains. To the best of our knowledge this is the first work to handleeither arbitrary arrival dynamics or an arbitrary downstream post-processing oforder quantities. Building upon recent work (Madeka et al., 2022) we similarlyformulate the periodic review inventory control problem as an exogenousdecision process, where most of the state is outside the control of the agent.Madeka et al., 2022 show how to construct a simulator that replays historicdata to solve this class of problem. In our case, we incorporate a deepgenerative model for the arrivals process as part of the history replay. Byformulating the problem as an exogenous decision process, we can apply resultsfrom Madeka et al., 2022 to obtain a reduction to supervised learning. Viasimulation studies we show that this approach yields statistically significantimprovements in profitability over production baselines. Using data from areal-world A/B test, we show that Gen-QOT generalizes well to off-policy dataand that the resulting buying policy outperforms traditional inventorymanagement systems in real world settings.

Learning an Inventory Control Policy with General Inventory Arrival Dynamics