Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2206.03934 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916375894687744 |
|---|---|
| author | Bagus, Benedikt Gepperth, Alexander |
| author_facet | Bagus, Benedikt Gepperth, Alexander |
| contents | We present an empirical study on the use of continual learning (CL) methods in a reinforcement learning (RL) scenario, which, to the best of our knowledge, has not been described before. CL is a very active recent research topic concerned with machine learning under non-stationary data distributions. Although this naturally applies to RL, the use of dedicated CL methods is still uncommon. This may be due to the fact that CL methods often assume a decomposition of CL problems into disjoint sub-tasks of stationary distribution, that the onset of these sub-tasks is known, and that sub-tasks are non-contradictory. In this study, we perform an empirical comparison of selected CL methods in a RL problem where a physically simulated robot must follow a racetrack by vision. In order to make CL methods applicable, we restrict the RL setting and introduce non-conflicting subtasks of known onset, which are however not disjoint and whose distribution, from the learner's point of view, is still non-stationary. Our results show that dedicated CL methods can significantly improve learning when compared to the baseline technique of "experience replay". |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2206_03934 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | A Study of Continual Learning Methods for Q-Learning Bagus, Benedikt Gepperth, Alexander Machine Learning We present an empirical study on the use of continual learning (CL) methods in a reinforcement learning (RL) scenario, which, to the best of our knowledge, has not been described before. CL is a very active recent research topic concerned with machine learning under non-stationary data distributions. Although this naturally applies to RL, the use of dedicated CL methods is still uncommon. This may be due to the fact that CL methods often assume a decomposition of CL problems into disjoint sub-tasks of stationary distribution, that the onset of these sub-tasks is known, and that sub-tasks are non-contradictory. In this study, we perform an empirical comparison of selected CL methods in a RL problem where a physically simulated robot must follow a racetrack by vision. In order to make CL methods applicable, we restrict the RL setting and introduce non-conflicting subtasks of known onset, which are however not disjoint and whose distribution, from the learner's point of view, is still non-stationary. Our results show that dedicated CL methods can significantly improve learning when compared to the baseline technique of "experience replay". |
| title | A Study of Continual Learning Methods for Q-Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2206.03934 |