Tsallis Entropy Regularization for Linearly Solvable MDP and Linear Quadratic Regulator
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909126907396096 |
|---|---|
| author | Hashizume, Yota Oishi, Koshi Kashima, Kenji |
| author_facet | Hashizume, Yota Oishi, Koshi Kashima, Kenji |
| contents | Shannon entropy regularization is widely adopted in optimal control due to its ability to promote exploration and enhance robustness, e.g., maximum entropy reinforcement learning known as Soft Actor-Critic. In this paper, Tsallis entropy, which is a one-parameter extension of Shannon entropy, is used for the regularization of linearly solvable MDP and linear quadratic regulators. We derive the solution for these problems and demonstrate its usefulness in balancing between exploration and sparsity of the obtained control law. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01805 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Tsallis Entropy Regularization for Linearly Solvable MDP and Linear Quadratic Regulator Hashizume, Yota Oishi, Koshi Kashima, Kenji Optimization and Control Machine Learning Systems and Control Shannon entropy regularization is widely adopted in optimal control due to its ability to promote exploration and enhance robustness, e.g., maximum entropy reinforcement learning known as Soft Actor-Critic. In this paper, Tsallis entropy, which is a one-parameter extension of Shannon entropy, is used for the regularization of linearly solvable MDP and linear quadratic regulators. We derive the solution for these problems and demonstrate its usefulness in balancing between exploration and sparsity of the obtained control law. |
| title | Tsallis Entropy Regularization for Linearly Solvable MDP and Linear Quadratic Regulator |
| topic | Optimization and Control Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2403.01805 |