Parameter Estimation using Reinforcement Learning Causal Curiosity: Limits and Challenges
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_ | 1866915286363406336 |
|---|---|
| author | Arana-Catania, Miguel Guo, Weisi |
| author_facet | Arana-Catania, Miguel Guo, Weisi |
| contents | Causal understanding is important in many disciplines of science and engineering, where we seek to understand how different factors in the system causally affect an experiment or situation and pave a pathway towards creating effective or optimising existing models. Examples of use cases are autonomous exploration and modelling of unknown environments or assessing key variables in optimising large complex systems. In this paper, we analyse a Reinforcement Learning approach called Causal Curiosity, which aims to estimate as accurately and efficiently as possible, without directly measuring them, the value of factors that causally determine the dynamics of a system. Whilst the idea presents a pathway forward, measurement accuracy is the foundation of methodology effectiveness. Focusing on the current causal curiosity's robotic manipulator, we present for the first time a measurement accuracy analysis of the future potentials and current limitations of this technique and an analysis of its sensitivity and confounding factor disentanglement capability - crucial for causal analysis. As a result of our work, we promote proposals for an improved and efficient design of Causal Curiosity methods to be applied to real-world complex scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_08453 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Parameter Estimation using Reinforcement Learning Causal Curiosity: Limits and Challenges Arana-Catania, Miguel Guo, Weisi Robotics Machine Learning Causal understanding is important in many disciplines of science and engineering, where we seek to understand how different factors in the system causally affect an experiment or situation and pave a pathway towards creating effective or optimising existing models. Examples of use cases are autonomous exploration and modelling of unknown environments or assessing key variables in optimising large complex systems. In this paper, we analyse a Reinforcement Learning approach called Causal Curiosity, which aims to estimate as accurately and efficiently as possible, without directly measuring them, the value of factors that causally determine the dynamics of a system. Whilst the idea presents a pathway forward, measurement accuracy is the foundation of methodology effectiveness. Focusing on the current causal curiosity's robotic manipulator, we present for the first time a measurement accuracy analysis of the future potentials and current limitations of this technique and an analysis of its sensitivity and confounding factor disentanglement capability - crucial for causal analysis. As a result of our work, we promote proposals for an improved and efficient design of Causal Curiosity methods to be applied to real-world complex scenarios. |
| title | Parameter Estimation using Reinforcement Learning Causal Curiosity: Limits and Challenges |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2505.08453 |