AI Paper Atlas

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

Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search

Lars Buesing, Theophane Weber, Yori Zwols, Nicolas Heess, Sebastien Racaniere, Arthur Guez, Jean-Baptiste Lespiau

ICLR 2019 · Reinforcement learning › Policy gradient and actor-critic · approach: Confounding-robust policy evaluation · 39 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
Anchor model rollouts in logged episodes by inferring scenarios counterfactuallyCF-GPS · PO-SOKOBANpolicy performanceImproved
Replace counterfactual scenario inference with an unconditional initial-state model (ablation)CF-GPS policy search · PO-SOKOBANpolicy performanceHurt
Condition scenario inference only on the first observation instead of hindsight data (ablation)CF-GPS policy search · PO-SOKOBANpolicy performanceHurt
Increase logged episode information used to infer initial scenarios (ablation)CF-PE · PO-SOKOBAN policy evaluationpolicy evaluation errorImproved
Use no real-data conditioning for scenario inference (ablation)CF-PE · PO-SOKOBAN policy evaluationpolicy evaluation errorHurt
Use Importance Sampling rather than counterfactual inferenceOff-policy policy evaluation · PO-SOKOBANrelative error: >0.8 relative errorHurt

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