تقرير
Learning Control Policies for Variable Objectives from Offline Data
العنوان: | Learning Control Policies for Variable Objectives from Offline Data |
---|---|
المؤلفون: | Weber, Marc, Swazinna, Phillip, Hein, Daniel, Udluft, Steffen, Sterzing, Volkmar |
المصدر: | 2023 IEEE Symposium Series on Computational Intelligence |
سنة النشر: | 2023 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Machine Learning |
الوصف: | Offline reinforcement learning provides a viable approach to obtain advanced control strategies for dynamical systems, in particular when direct interaction with the environment is not available. In this paper, we introduce a conceptual extension for model-based policy search methods, called variable objective policy (VOP). With this approach, policies are trained to generalize efficiently over a variety of objectives, which parameterize the reward function. We demonstrate that by altering the objectives passed as input to the policy, users gain the freedom to adjust its behavior or re-balance optimization targets at runtime, without need for collecting additional observation batches or re-training. Comment: 8 pages, 7 figures |
نوع الوثيقة: | Working Paper |
DOI: | 10.1109/SSCI52147.2023.10371978 |
URL الوصول: | http://arxiv.org/abs/2308.06127 |
رقم الأكسشن: | edsarx.2308.06127 |
قاعدة البيانات: | arXiv |
DOI: | 10.1109/SSCI52147.2023.10371978 |
---|