Papers › Model-Bellman Inconsistency for Model-based Offline Reinforcement Learning

Model-Bellman Inconsistency for Model-based Offline Reinforcement Learning

1 Jul 2023PMLR 2023 7archive 2025-07-28

Yihao Sun, Jiaji Zhang, Chengxing Jia, Haoxin Lin, Junyin Ye, Yang Yu

For offline reinforcement learning (RL), model-based methods are expected to be data-efficient as they incorporate dynamics models to generate more data. However, due to inevitable model errors, straightforwardly learning a policy in the model typically fails in the offline setting. Previous studies have incorporated conservatism to prevent out-of-distribution exploration. For example, MOPO penalizes rewards through uncertainty measures from predicting the next states, which we have discovered are loose bounds of the ideal uncertainty, i.e., the Bellman error. In this work, we propose MOdel-Bellman Inconsistency penalized offLinE Policy Optimization (MOBILE), a novel uncertainty-driven offline RL algorithm. MOBILE conducts uncertainty quantification through the inconsistency of Bellman estimations under an ensemble of learned dynamics models, which can be a better approximator to the true Bellman error, and penalizes the Bellman estimation based on this uncertainty. Empirically we have verified that our proposed uncertainty quantification can be significantly closer to the true Bellman error than the compared methods. Consequently, MOBILE outperforms prior offline RL approaches on most tasks of D4RL and NeoRL benchmarks.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

yihaosun1124/mobile officialmentioned in paperpytorchSyntology: not harvested report
yihaosun1124/OfflineRL-Kit mentioned in paperpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MOPO: Model-based Offline Policy Optimization (arXiv:2005.13239; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified), COMBO: Conservative Offline Model-Based Policy Optimization (arXiv:2102.08363; that paper's own run record: 0 ran · 2 unverified), Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble (arXiv:2110.01548; that paper's own run record: 13 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

D4RLOffline RLReinforcement LearningReinforcement Learning (RL)Uncertainty Quantificationmodelreinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections