AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation

Yuta Saito, Shunsuke Aihara, Megumi Matsutani, Yusuke Narita

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: RL with tree search for discovery · 5 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
use DRos with automatic hyperparameter tuning instead of DROPE estimators · Open Bandit Dataset ALL, Bernoulli TS -> RandomRMSE: 0.482 -> 0.316Improved
use DRos instead of IPWOPE estimators · Open Bandit Dataset ALL, Bernoulli TS -> RandomRMSE: 0.493 -> 0.316Improved
increase DRos lambda from 1 to 1,000 (ablation)DRos · Open Bandit Dataset ALL, Bernoulli TS -> RandomRMSE: 0.963 -> 0.245Improved
increase DRos lambda from 1,000 to 10,000 (ablation)DRos · Open Bandit Dataset ALL, Bernoulli TS -> RandomRMSE: 0.245 -> 0.323Hurt
increase DRos lambda from 1 to 5,000 (ablation)DRos · Open Bandit Dataset ALL, Random -> Bernoulli TSRMSE: 1.384 -> 0.476Improved
use automatic lambda tuning instead of best fixed lambda (ablation)DRos · Open Bandit Dataset ALL, Bernoulli TS -> RandomRMSE: 0.245 -> 0.323Hurt
use automatic lambda tuning instead of lambda=1,000 (ablation)DRos · Open Bandit Dataset ALL, Random -> Bernoulli TSRMSE: 0.476 -> 0.476No clear effect
use small sample (n=10,000) instead of large (n=300,000) for DMDM · Open Bandit Dataset ALL, Bernoulli TS -> RandomRMSE: 1.026 -> 0.797Improved
use small sample (n=10,000) instead of large (n=300,000) for DRosDRos · Open Bandit Dataset ALL, Bernoulli TS -> RandomRMSE: 0.316 -> 0.765Hurt
replace logistic regression with gradient boosting reward estimator (ablation)DM · Open Bandit Dataset ALL, Bernoulli TS -> RandomRMSE: 1.597 -> 1.026Improved
replace logistic regression with gradient boosting reward estimator (ablation)DR · Open Bandit Dataset ALL, Bernoulli TS -> RandomRMSE: 2.250 -> 0.482Improved
replace logistic regression with gradient boosting reward estimator (ablation)DRos · Open Bandit Dataset ALL, Bernoulli TS -> RandomRMSE: 2.065 -> 0.316Improved

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