Offline Multitask Representation Learning for Reinforcement Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913568713080832 |
|---|---|
| author | Ishfaq, Haque Nguyen-Tang, Thanh Feng, Songtao Arora, Raman Wang, Mengdi Yin, Ming Precup, Doina |
| author_facet | Ishfaq, Haque Nguyen-Tang, Thanh Feng, Songtao Arora, Raman Wang, Mengdi Yin, Ming Precup, Doina |
| contents | We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common representation and is asked to learn the shared representation. We theoretically investigate offline multitask low-rank RL, and propose a new algorithm called MORL for offline multitask representation learning. Furthermore, we examine downstream RL in reward-free, offline and online scenarios, where a new task is introduced to the agent that shares the same representation as the upstream offline tasks. Our theoretical results demonstrate the benefits of using the learned representation from the upstream offline task instead of directly learning the representation of the low-rank model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_11574 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Offline Multitask Representation Learning for Reinforcement Learning Ishfaq, Haque Nguyen-Tang, Thanh Feng, Songtao Arora, Raman Wang, Mengdi Yin, Ming Precup, Doina Machine Learning We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common representation and is asked to learn the shared representation. We theoretically investigate offline multitask low-rank RL, and propose a new algorithm called MORL for offline multitask representation learning. Furthermore, we examine downstream RL in reward-free, offline and online scenarios, where a new task is introduced to the agent that shares the same representation as the upstream offline tasks. Our theoretical results demonstrate the benefits of using the learned representation from the upstream offline task instead of directly learning the representation of the low-rank model. |
| title | Offline Multitask Representation Learning for Reinforcement Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2403.11574 |