Critic as Lyapunov function (CALF): a model-free, stability-ensuring agent
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910605133217792 |
|---|---|
| author | Osinenko, Pavel Yaremenko, Grigory Zashchitin, Roman Bolychev, Anton Ibrahim, Sinan Dobriborsci, Dmitrii |
| author_facet | Osinenko, Pavel Yaremenko, Grigory Zashchitin, Roman Bolychev, Anton Ibrahim, Sinan Dobriborsci, Dmitrii |
| contents | This work presents and showcases a novel reinforcement learning agent called Critic As Lyapunov Function (CALF) which is model-free and ensures online environment, in other words, dynamical system stabilization. Online means that in each learning episode, the said environment is stabilized. This, as demonstrated in a case study with a mobile robot simulator, greatly improves the overall learning performance. The base actor-critic scheme of CALF is analogous to SARSA. The latter did not show any success in reaching the target in our studies. However, a modified version thereof, called SARSA-m here, did succeed in some learning scenarios. Still, CALF greatly outperformed the said approach. CALF was also demonstrated to improve a nominal stabilizer provided to it. In summary, the presented agent may be considered a viable approach to fusing classical control with reinforcement learning. Its concurrent approaches are mostly either offline or model-based, like, for instance, those that fuse model-predictive control into the agent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09869 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Critic as Lyapunov function (CALF): a model-free, stability-ensuring agent Osinenko, Pavel Yaremenko, Grigory Zashchitin, Roman Bolychev, Anton Ibrahim, Sinan Dobriborsci, Dmitrii Robotics Artificial Intelligence Optimization and Control This work presents and showcases a novel reinforcement learning agent called Critic As Lyapunov Function (CALF) which is model-free and ensures online environment, in other words, dynamical system stabilization. Online means that in each learning episode, the said environment is stabilized. This, as demonstrated in a case study with a mobile robot simulator, greatly improves the overall learning performance. The base actor-critic scheme of CALF is analogous to SARSA. The latter did not show any success in reaching the target in our studies. However, a modified version thereof, called SARSA-m here, did succeed in some learning scenarios. Still, CALF greatly outperformed the said approach. CALF was also demonstrated to improve a nominal stabilizer provided to it. In summary, the presented agent may be considered a viable approach to fusing classical control with reinforcement learning. Its concurrent approaches are mostly either offline or model-based, like, for instance, those that fuse model-predictive control into the agent. |
| title | Critic as Lyapunov function (CALF): a model-free, stability-ensuring agent |
| topic | Robotics Artificial Intelligence Optimization and Control |
| url | https://arxiv.org/abs/2409.09869 |