AI Paper Atlas

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

Off-Policy Evaluation for Action-Dependent Non-stationary Environments

Yash Chandak, Shiv Shankar, Nathaniel D. Bastian, Bruno Castro da Silva, Emma Brunskill, Philip S. Thomas

NeurIPS 2022 · Reinforcement learning › Policy gradient and actor-critic · approach: Confounding-robust policy evaluation · 3 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 OPEN instead of WIS for non-stationary environmentsOff-policy evaluation · Non-stationary Mountain Car, Type-1 Diabetes Management, MEDEVAC, and RoboToyabsolute bias and mean-squared errorImproved
Use OPEN instead of Pro-WLS in active or hybrid non-stationarityOff-policy evaluation · Non-stationary Mountain Car, MEDEVAC, and RoboToyabsolute bias and mean-squared errorImproved
Use OPEN instead of Pro-WLS in passive non-stationarityOff-policy evaluation · Type-1 Diabetes Managementabsolute bias and mean-squared errorImproved
Increase the rate of non-stationarityWIS · Non-stationary domainsabsolute biasHurt
Use OPEN's autoregressive forecasting rather than Pro-WLS's Fourier-basis regressionHyperparameter robustness · Non-stationary domainsforecasting robustnessImproved
Use importance-weighted instrumental-variable regression instead of naive least-squares regression on noisy performance estimates (ablation)OPEN · Linear performance-transition modelparameter-estimation consistencyImproved
Normalize importance weights on the squared error rather than importance-weighting the regression target (ablation)OPEN · Linear performance-transition modelparameter-estimation varianceImproved
Use a second importance-sampling correction for the effect of behavior-policy actions on the next environment (ablation)OPEN · Active or hybrid non-stationarityfuture-performance predictionImproved
Use importance-weighted regression at high rates of non-stationarity (ablation)OPEN · Non-stationary domains at high change ratesmean-squared errorMixed

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