Path Integral Bottleneck: An Algorithm-Agnostic Framework of Computation and Control
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915529876307968 |
|---|---|
| author | Ting, Justin Li, Jing Shuang |
| author_facet | Ting, Justin Li, Jing Shuang |
| contents | Executing a control sequence requires computation. While this is a simple observation, developing a framework that relates a controller's required computation to its ability to successfully control a system (e.g. lower control cost) is challenging, especially when the controller appears on alternative compute platforms (e.g. biological neural networks). More specifically, we want a framework where, given an observed closed-loop trajectory, we can quantify the computation effort needed to produce that trajectory. To enable effective comparisons of closed-loop systems across alternative compute platforms, we present the Path Integral Bottleneck (PI-IB), a method to produce an analytical, algorithm-agnostic description of the compute-control relationship. With the PI-IB framework, we can plot tradeoffs between performance and computation effort for any given plant description and control cost function. Simulations of the cart-pole reveal fundamental control-compute tradeoffs, exposing regions where the task performance-per-compute is higher than others. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_09896 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Path Integral Bottleneck: An Algorithm-Agnostic Framework of Computation and Control Ting, Justin Li, Jing Shuang Systems and Control Executing a control sequence requires computation. While this is a simple observation, developing a framework that relates a controller's required computation to its ability to successfully control a system (e.g. lower control cost) is challenging, especially when the controller appears on alternative compute platforms (e.g. biological neural networks). More specifically, we want a framework where, given an observed closed-loop trajectory, we can quantify the computation effort needed to produce that trajectory. To enable effective comparisons of closed-loop systems across alternative compute platforms, we present the Path Integral Bottleneck (PI-IB), a method to produce an analytical, algorithm-agnostic description of the compute-control relationship. With the PI-IB framework, we can plot tradeoffs between performance and computation effort for any given plant description and control cost function. Simulations of the cart-pole reveal fundamental control-compute tradeoffs, exposing regions where the task performance-per-compute is higher than others. |
| title | Path Integral Bottleneck: An Algorithm-Agnostic Framework of Computation and Control |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2505.09896 |