AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Off-Policy Evaluation via the Regularized Lagrangian

Mengjiao Yang, Ofir Nachum, Bo Dai, Lihong Li, Dale Schuurmans

NeurIPS 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Importance-weighted OPE estimators · 19 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 dual estimator instead of primal estimator (ablation)DICE regularized Lagrangian OPE · Grid, Reacher, CartpoleOPE estimation errorImproved
use Lagrangian estimator instead of dual estimator (ablation)DICE regularized Lagrangian OPE · Grid, Reacher, CartpoleOPE estimation varianceHurt
regularize dual variable instead of primal variable (with reward scaling on) (ablation)dual estimator · Grid, Reacher, Cartpoleestimation biasImproved
set reward scaling alpha_R=1 vs 0 under dual regularization (ablation)dual estimator · Grid, Reacher, Cartpoleestimate accuracyNo clear effect
add normalization constraint (lambda) (ablation)dual estimator with dual regularization · Grid, Reacher, Cartpoletraining stability and approximation errorImproved
add positivity constraint on zeta (ablation)dual estimator with dual regularization · Grid, Reacher, Cartpoleoptimization stability and accuracyImproved
solve unconstrained primal form instead of Lagrangian minimax (ablation)dual estimator · Grid and Cartpole (discrete actions)estimation variance/accuracyImproved
solve unconstrained primal form instead of Lagrangian minimax (ablation)dual estimator · Reacher (continuous actions)estimation biasHurt
transform rewards by scaling or shiftingdual estimator vs primal/Lagrangian estimators · Grid, linear and neural parametrizationestimate robustnessMixed

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