AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Efficient Offline Reinforcement Learning via Peer-Influenced Constraint

Yujia Zhang, Lin Li, Wei Wei, Jianguo Wu, Yi Ma, Jiye Liang

ICLR 2026 · Reinforcement learning › Offline RL · approach: Simple practical 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
add critic ensemble to PIC-TD3 (EPIC) (ablation)PIC-TD3 · Gym-MuJoCo averagenormalized score: 85.1 -> 87.8Improved
add critic ensemble to PIC-TD3 (EPIC) (ablation)PIC-TD3 · AntMaze averagenormalized score: 75.6 -> 82.9Improved
add critic ensemble to PIC-TD3 (EPIC) (ablation)PIC-TD3 · Adroit averagenormalized score: 53.8 -> 62.5Improved
replace behavior-cloning constraint with peer-influenced constraintTD3+BC · Gym-MuJoCo averagenormalized score: 70.4 -> 85.1Improved
replace behavior-cloning constraint with peer-influenced constraintTD3+BC · Adroit averagenormalized score: 49.9 -> 53.8Improved
replace behavior-cloning constraint with peer-influenced constraintTD3+BC · AntMaze averagenormalized score: 28.8 -> 75.6Improved
add PIC to IQLIQL · AntMaze averagenormalized score: 58.4 -> 78.7Improved
use one shared hyperparameter setting (delta=1) across all Gym-MuJoCo tasks (ablation)EPIC · Gym-MuJoCo averagenormalized score: 87.8 -> 86.8No clear effect
use one shared hyperparameter setting (delta=2) across all Gym-MuJoCo tasks (ablation)EPIC · Gym-MuJoCo averagenormalized score: 87.8 -> 87.3No clear effect
increase PIC strength delta (ablation)EPIC with critic ensembles · hopper-medium-expertQmin / Qstd uncertaintyImproved
increase number of peer states K beyond 20 (ablation)PIC-TD3 and EPIC · Gym-MuJoCo tasksnormalized returnMixed
set PIC strength delta below 1 or above 4 (ablation)EPIC · hopper-mediumnormalized returnHurt

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