AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting

Zhongjian Qiao, Jiafei Lyu, Boxiang Lyu, Yao Shu, Siyang Gao, Shuang Qiu

ICLR 2026 · Reinforcement learning › Offline RL · approach: Pessimism and uncertainty in offline RL · 2 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 RAMBO with ROMI (robust value-aware model learning plus adaptive weighting)RAMBO · D4RL MuJoCo (12 datasets, total)total normalized score: 804.1 -> 953.5Improved
replace RAMBO with ROMIRAMBO · NeoRL (9 datasets, total)total normalized score: 382.8 -> 472.2Improved
replace MOBILE with ROMIMOBILE · D4RL MuJoCo (12 datasets, total)total normalized score: 857.7 -> 953.5Improved
replace Count-MORL with ROMICount-MORL · D4RL MuJoCo (12 datasets, total)total normalized score: 927.5 -> 953.5Improved
replace RAMBO with ROMI on hopper-medium-replayRAMBO · D4RL hopper-medium-replay-v2normalized score: 77.2 -> 102.0Improved
replace RAMBO with ROMI on walker2d-medium-expertRAMBO · D4RL walker2d-medium-expert-v2normalized score: 73.7 -> 113.3Improved
replace RAMBO with ROMI on halfcheetah-mediumRAMBO · D4RL halfcheetah-medium-v2normalized score: 76.2 -> 76.2No clear effect
replace CQL with ROMI on NeoRLCQL · NeoRL (9 datasets, total)total normalized score: 466.3 -> 472.2Improved
add implicitly differentiable adaptive weighting to robust value-aware model learning (ablation)ROMI · halfcheetah-medium-replay and hopper-medium-replaymodel prediction error and normalized scoreImproved
increase RAMBO adversarial coefficient lambda from 3e-4 to 5e-2 or 1e-1 (ablation)RAMBO · halfcheetah-medium-expert-v2Q-value estimate: 3e-4 -> 5e-2, 1e-1Hurt
vary RAMBO lambda among 0, 3e-4, 5e-3 (ablation)RAMBO · halfcheetah-medium-expert-v2Q-value estimate: 0, 3e-4, 5e-3No clear effect
increase uncertainty set scale xi from 0.01 to 10 (ablation)ROMI · halfcheetah-medium-expert-v2Q-value estimate and training stability: 0.01, 0.1, 1.0, 10Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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