AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Reliability-Guaranteed and Reward-Seeking Sequence Modeling for Model-Based Offline Reinforcement Learning

Shenghong He, Chao Yu, Qian Lin, Yile Liang, Donghui Li, Xuetao Ding

AAAI 2026 · Reinforcement learning › Offline RL · approach: Simple practical offline RL · 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
augment data with RTBCQ · D4RL Maze2D-medium (sparse)normalized return: 18.2 -> 55.3Improved
augment data with RTBCQ · D4RL Antmaze-medium (diverse)normalized return: 5.2 -> 56.4Improved
augment data with RTIQL · D4RL Hopper medium-replaynormalized return: 96.8 -> 108.3Improved
augment data with RTIQL · D4RL Maze2D-umaze (sparse)normalized return: 20.1 -> 44.3Mixed
add reliability estimation to generation length (ablation)RT · D4RL (IQL)normalized returnImproved
generate backward instead of forward (ablation)RT+BCQ · Maze2D and Antmazenormalized returnImproved
use RT instead of ROMI/CABI/TATU/DStitch augmentationscheduling policy · Industrial OFD dataTCR: 7 -> 10Improved
set reliability penalty beta to a moderate value (ablation)RT+IQL · D4RL Hopper/Walker/Maze2D/Antmaze mediumnormalized returnMixed

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