Amortized Low-Rank Adaptation for Model-Based Reinforcement Learning

T1Covered by 1 source · first reported by arXiv at 24 Sept, 04:00 UTC

arXiv:2609.12278v2 Announce Type: replace-cross Abstract: World models let agents plan by predicting the consequences of their actions, but changes in the environment can make them inaccurate. We study the problem of adapting a world model to an unknown test-time environment, drawn from a known…

science

Sources

• T1Amortized Low-Rank Adaptation for Model-Based Reinforcement LearningarXiv24 Sept, 04:00