AI Paper Atlas

Research map / Reinforcement learning / Offline RL

BCORLE($\lambda$): An Offline Reinforcement Learning and Evaluation Framework for Coupons Allocation in E-commerce Market

Yang Zhang, Bo Tang, Qingyu Yang, Dou An, Hongyin Tang, Chenyang Xi, Xueying LI, Feiyu Xiong

NeurIPS 2021 · Reinforcement learning › Offline RL · approach: Offline RL sample complexity theory · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace lambda-update training with lambda-generalizationR-BCQ policy learning · Simulation (stop at AvgCost 7.0, AvgLogins 15)episodes and training time: 14000 -> 3000 episodes; 2.187h -> 0.439hImproved
add REME OPE instead of DR/IS (simulation)OPE of R-BCQ · Simulation lambda=0, ls=1000AvgLogins error (days): 3.7837 -> 0.0135Improved
use REME instead of FQEOPE of R-BCQ · Simulation lambda=0, ls=4000AvgLogins error (days): 0.0644 -> 0.0158Improved
use REME instead of DMOPE of R-BCQ · Simulation lambda=1, ls=1000AvgLogins error (days): 0.0192 -> 0.0100Improved
use REME instead of IS onlineOPE of R-BCQ · Taobao Deals onlineAvgLogins error (days): 0.2203 -> 0.0443Improved
use REME instead of FQE onlineOPE of R-BCQ · Taobao Deals onlineAvgCost error (Yuan): 0.1515 -> 0.0221Improved
replace uplift LR+LP with offline RL R-BCQcoupon allocation · Taobao Deals online week 1ROI improvement: 15.47%Improved
replace GBDT+LP with R-BCQcoupon allocation · Taobao Deals online week 2ROI (days/Yuan): 1.3201 -> 1.4773Improved
swap BCQ for R-BCQoffline RL algorithm · Taobao Deals online week 1ROI (days/Yuan): 1.3950 -> 1.4329Improved
swap REM for R-BCQoffline RL algorithm · Taobao Deals online week 2AvgLogins (days): 5.9092 -> 5.9871Improved
swap GBDT+LP for LR+LP (uplift model choice)uplift baseline · Taobao Deals online week 1ROI Imp: -0.31%No clear effect
use model-based MOPO instead of model-free R-BCQ/BCQ/REMoffline RL · SimulationAvgCostHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy