Learning Control Policies for Variable Objectives from Offline Data
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911746096103424 |
|---|---|
| author | Weber, Marc Swazinna, Phillip Hein, Daniel Udluft, Steffen Sterzing, Volkmar |
| author_facet | Weber, Marc Swazinna, Phillip Hein, Daniel Udluft, Steffen Sterzing, Volkmar |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_06127 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Learning Control Policies for Variable Objectives from Offline Data Weber, Marc Swazinna, Phillip Hein, Daniel Udluft, Steffen Sterzing, Volkmar Machine Learning 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. |
| title | Learning Control Policies for Variable Objectives from Offline Data |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2308.06127 |