AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Data-Driven Offline Decision-Making via Invariant Representation Learning

Han Qi, Yi Su, Aviral Kumar, Sergey Levine

NeurIPS 2022 · Reinforcement learning › Offline RL · approach: Simple practical offline RL · 1 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 invariant representation regularization (IOM) instead of the compared prior methodsOffline model-based optimization · Design-Bench tasks (aggregate)normalized scoreImproved
Add a conservatism term to IOM (IOM-C) (ablation)IOM · Design-Bench tasks (aggregate)normalized scoreNo clear effect
Use chi-squared discrepancy rather than MMD (ablation)IOM · Design-Bench tasksnormalized scoreImproved
Tune IOM with validation prediction error and an invariance filterIOM · Design-Bench tasks (aggregate)normalized score relative to oracle tuningImproved
Tune IOM using validation prediction error only (ablation)IOM · Design-Bench tasks (aggregate)normalized score relative to oracle tuningHurt
Tune IOM using the invariance regularizer only (ablation)IOM · Design-Bench tasks (aggregate)normalized score relative to oracle tuningHurt
Use uniform checkpoint selection instead of validation-error checkpoint selection (ablation)IOM offline tuning · Design-Bench tasksobjective valueHurt
Select checkpoints using validation prediction errorIOM · Design-Bench tasksobjective valueImproved
Vary the quantile used to filter models by invariance (ablation)IOM offline tuning · Design-Bench tasks (aggregate)normalized score relative to oracle tuningNo clear effect
Use offline validation-based tuning rather than oracle online tuning (ablation)COMs and gradient-ascent objective models · Design-Bench tasks (aggregate)normalized score relative to oracle tuningHurt

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