On Tackling Complex Tasks with Reward Machines and Signal Temporal Logics
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910133171257344 |
|---|---|
| author | Ruiz, Ana María Gómez Dang, Thao Donzé, Alexandre |
| author_facet | Ruiz, Ana María Gómez Dang, Thao Donzé, Alexandre |
| contents | We propose a Reinforcement Learning (RL) based control design framework for handling complex tasks. The approach extends the concept of Reward Machines (RM) with Signal Temporal Logic (STL) formulas that can be used for event generation. The use of STL allows not only a more efficient representation of rewards for complex tasks but also guiding the training process to converge towards behaviors satisfying specified requirements. We also propose an implementation of the framework that leverages the STL online monitoring algorithms. We illustrate the framework with three case studies (minigrid, cart-pole and high-way environments) with non-trivial tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_14440 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | On Tackling Complex Tasks with Reward Machines and Signal Temporal Logics Ruiz, Ana María Gómez Dang, Thao Donzé, Alexandre Artificial Intelligence We propose a Reinforcement Learning (RL) based control design framework for handling complex tasks. The approach extends the concept of Reward Machines (RM) with Signal Temporal Logic (STL) formulas that can be used for event generation. The use of STL allows not only a more efficient representation of rewards for complex tasks but also guiding the training process to converge towards behaviors satisfying specified requirements. We also propose an implementation of the framework that leverages the STL online monitoring algorithms. We illustrate the framework with three case studies (minigrid, cart-pole and high-way environments) with non-trivial tasks. |
| title | On Tackling Complex Tasks with Reward Machines and Signal Temporal Logics |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.14440 |