.png){kind=icon}
.png){kind=icon}
Return
Enhancing Offline Model-Based RL via Active Model Selection: A Bayesian Optimization Perspective
.png){kind=icon}
OA
AI
Y
W
Y
X
P
DOI：10.1007/s10994-026-07119-6.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Offline model-based reinforcement learning (MBRL) serves as a competitive framework that can learn well-performing policies solely from pre-collected data with the help of learned dynamics models. To fully unleash the power of offline MBRL, model selection plays a pivotal role in determining the dynamics model utilized for downstream policy learning. However, offline MBRL conventionally relies on validation or off-policy evaluation, which are rather inaccurate due to the inherent distribution shift in offline RL. To tackle this, we propose BOMS, an active model selection framework that enhances model selection in offline MBRL with only a small online interaction budget, through the lens of Bayesian optimization (BO). Specifically, we recast model selection as BO and enable probabilistic inference in BOMS by proposing a novel model-induced kernel, which is theoretically grounded and computationally efficient. Through extensive experiments, we show that BOMS improves over the baseline methods with a small amount of online interaction comparable to only $$1\%$$ - $$2.5\%$$ of offline training data on various RL tasks.
Keywords:
Offline reinforcement learning
Bayesian optimization
Dynamics model selection
Dynamics model distance
Gaussian process
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.9
Papers:
2.6K
Citations:
3.4W
Organization
Cited Papers