AI Paper Atlas

Research map / Reinforcement learning / Offline RL

REG: In-Sample RL via Regularizing the Evaluation Gap

Hanpu Shen, Weining Shen, Roy Fox

ICML 2026 · Reinforcement learning › Offline RL · approach: Behavior regularization for offline RL

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 orthogonal policy gradient (OPG) instead of weighted behavior cloning only for policy extraction (ablation)REG · D4RL MuJoCo locomotion (medium, medium-replay, medium-expert)average normalized scoreImproved
use OPG instead of WBC-only on medium-expert datasets (ablation)REG · D4RL MuJoCo medium-expertaverage normalized scoreImproved
increase value conservatism alpha on medium and medium-replay datasets (ablation)REG · D4RL MuJoCo medium and medium-replaynormalized scoreImproved
lower alpha on expert datasets (ablation)REG · D4RL MuJoCo medium-expertnormalized scoreNo clear effect
set OPG strength lambda to an intermediate value in [0.2, 0.5] rather than lower or higher (ablation)REG · D4RL MuJoCo medium and medium-replaynormalized score: peak at lambda in [0.2, 0.5]Improved
use excessively large lambda for the orthogonal gradient (ablation)REG · D4RL expert-level datasetsnormalized scoreHurt
use Gaussian-policy REG instead of Gaussian-policy IQLIQL · D4RL AntMaze averagenormalized score: 57.2 -> 77.5Improved
use REG instead of IVRIVR · D4RL Locomotion averagenormalized score: 83.3 -> 87.8Improved
use REG instead of ReBRACReBRAC · D4RL Locomotion averagenormalized score: 88.4 -> 87.8No clear effect
use REG with Gaussian policy instead of IDQL diffusion policyIDQL · D4RL AntMaze averagenormalized score: 79.2 -> 77.5No clear effect

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