OpTTA：面向规划的乐观测试时世界模型自适应方法
Adapt for Planning, Not just Prediction: Optimistic Test-Time World Model Adaptation
AI 导读
研究者提出乐观测试时自适应方法 OpTTA，在规划目标下对潜在世界模型做测试时自适应。其目标函数同时最小化观测转移的预测损失和规划器候选 rollout 的目标达成成本，使模型朝乐观方向偏置且无需额外环境交互。
正文 · 原文
Abstract:Latent world models are typically pre-trained offline and kept frozen at test time, so planning with them can degrade under distribution shift. Test-time adaptation (TTA) can mitigate this degradation by updating the model during deployment. Unlike pre-training on fixed data, TTA for planning is closed-loop: the planner uses model rollouts to select actions, and the resulting transitions drive the next update. This raises the question: which objective should guide TTA for planning? Under a prediction-only objective, the model is fit only to the outcomes of its own actions, so it can remain wrong about the actions that would reach the goal, and low prediction error need not translate into better planning. Inspired by reward-biased maximum likelihood from adaptive control, we introduce Optimistic Test-Time Adaptation (OpTTA). Its objective has two terms, the prediction loss on observed transitions and the planner's goal-reaching cost on its candidate rollouts, both minimized over the model parameters. The planning term biases adaptation toward models that are optimistic about reaching the goal, without any additional environment interaction. Across visual and environment shifts on manipulation, reaching and navigation tasks, OpTTA raises final planning success over the frozen model by 13.5 percentage points on average, compared with 6.9 for the prediction-only objective (AdaJEPA), when only the predictor is adapted. When the encoder is adapted as well, the gains are 13.5 and 7.5 points. These experiments span three JEPA world models with different encoders and training objectives and, for temporal straightening, both CEM and gradient-based planners. Our results suggest that test-time adaptation of world models for planning benefits from an optimistic, task-aware term in addition to the prediction loss.
| Comments: | Accepted at the CoRL 2026 Workshop on Pretrain to Adapt |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Robotics (cs.RO) |
| Cite as: | arXiv:2610.35636 [cs.LG] |
| (or arXiv:2610.35636v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35636 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Akshay Mete [view email]
[v1]
Mon, 26 Oct 2026 15:46:17 UTC (562 KB)
来源：arXiv cs.AI · arxiv.org