AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage

Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun

NeurIPS 2023 · Reinforcement learning › Offline RL · approach: Offline RL sample complexity theory · 0 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
Replace a hard-margin requirement with the soft-margin conditionMQP · Offline RLassumption stringencyImproved
Require coverage only for a single comparator policy rather than uniformly over policiesMSQP and MQP · Offline RLcoverage requirementImproved
Use refined, function-class-adaptive concentrability instead of requiring a finite density ratio for the initial distributionMSQP · Offline RL with initial-distribution shiftcoverage applicabilityImproved
Use minimax objectives designed for L2 estimation rather than Bellman-residual guarantees aloneMSQP and MQP · Offline RL with general function approximationL2-error guaranteeImproved
Relax the Bellman equality constraint to an inequality in the minimum-norm formulationMSQP and MQP · Offline RLexistence of a convex minimax formulationImproved

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