Enhancing Reinforcement Learning Agents with Local Guides
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929421086097408 |
|---|---|
| author | Daoudi, Paul Robu, Bogdan Prieur, Christophe Santos, Ludovic Dos Barlier, Merwan |
| author_facet | Daoudi, Paul Robu, Bogdan Prieur, Christophe Santos, Ludovic Dos Barlier, Merwan |
| contents | This paper addresses the problem of integrating local guide policies into a Reinforcement Learning agent. For this, we show how to adapt existing algorithms to this setting before introducing a novel algorithm based on a noisy policy-switching procedure. This approach builds on a proper Approximate Policy Evaluation (APE) scheme to provide a perturbation that carefully leads the local guides towards better actions. We evaluated our method on a set of classical Reinforcement Learning problems, including safety-critical systems where the agent cannot enter some areas at the risk of triggering catastrophic consequences. In all the proposed environments, our agent proved to be efficient at leveraging those policies to improve the performance of any APE-based Reinforcement Learning algorithm, especially in its first learning stages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13930 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Reinforcement Learning Agents with Local Guides Daoudi, Paul Robu, Bogdan Prieur, Christophe Santos, Ludovic Dos Barlier, Merwan Machine Learning Systems and Control This paper addresses the problem of integrating local guide policies into a Reinforcement Learning agent. For this, we show how to adapt existing algorithms to this setting before introducing a novel algorithm based on a noisy policy-switching procedure. This approach builds on a proper Approximate Policy Evaluation (APE) scheme to provide a perturbation that carefully leads the local guides towards better actions. We evaluated our method on a set of classical Reinforcement Learning problems, including safety-critical systems where the agent cannot enter some areas at the risk of triggering catastrophic consequences. In all the proposed environments, our agent proved to be efficient at leveraging those policies to improve the performance of any APE-based Reinforcement Learning algorithm, especially in its first learning stages. |
| title | Enhancing Reinforcement Learning Agents with Local Guides |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2402.13930 |