Reduce, Reuse, Recycle: Categories for Compositional Reinforcement Learning
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_ | 1866916650095214592 |
|---|---|
| author | Bakirtzis, Georgios Savvas, Michail Zhao, Ruihan Chinchali, Sandeep Topcu, Ufuk |
| author_facet | Bakirtzis, Georgios Savvas, Michail Zhao, Ruihan Chinchali, Sandeep Topcu, Ufuk |
| contents | In reinforcement learning, conducting task composition by forming cohesive, executable sequences from multiple tasks remains challenging. However, the ability to (de)compose tasks is a linchpin in developing robotic systems capable of learning complex behaviors. Yet, compositional reinforcement learning is beset with difficulties, including the high dimensionality of the problem space, scarcity of rewards, and absence of system robustness after task composition. To surmount these challenges, we view task composition through the prism of category theory -- a mathematical discipline exploring structures and their compositional relationships. The categorical properties of Markov decision processes untangle complex tasks into manageable sub-tasks, allowing for strategical reduction of dimensionality, facilitating more tractable reward structures, and bolstering system robustness. Experimental results support the categorical theory of reinforcement learning by enabling skill reduction, reuse, and recycling when learning complex robotic arm tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_13376 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Reduce, Reuse, Recycle: Categories for Compositional Reinforcement Learning Bakirtzis, Georgios Savvas, Michail Zhao, Ruihan Chinchali, Sandeep Topcu, Ufuk Artificial Intelligence Machine Learning Systems and Control Category Theory In reinforcement learning, conducting task composition by forming cohesive, executable sequences from multiple tasks remains challenging. However, the ability to (de)compose tasks is a linchpin in developing robotic systems capable of learning complex behaviors. Yet, compositional reinforcement learning is beset with difficulties, including the high dimensionality of the problem space, scarcity of rewards, and absence of system robustness after task composition. To surmount these challenges, we view task composition through the prism of category theory -- a mathematical discipline exploring structures and their compositional relationships. The categorical properties of Markov decision processes untangle complex tasks into manageable sub-tasks, allowing for strategical reduction of dimensionality, facilitating more tractable reward structures, and bolstering system robustness. Experimental results support the categorical theory of reinforcement learning by enabling skill reduction, reuse, and recycling when learning complex robotic arm tasks. |
| title | Reduce, Reuse, Recycle: Categories for Compositional Reinforcement Learning |
| topic | Artificial Intelligence Machine Learning Systems and Control Category Theory |
| url | https://arxiv.org/abs/2408.13376 |