Preprint
Reduce, Reuse, Recycle: Categories for Compositional Reinforcement Learning
arXiv.org
Cornell University
08/23/2024
DOI: 10.48550/arxiv.2408.13376
Abstract
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.
Details
- Title: Subtitle
- Reduce, Reuse, Recycle: Categories for Compositional Reinforcement Learning
- Creators
- Georgios BakirtzisMichail Savvas - University of IowaRuihan Zhao - The University of Texas at AustinSandeep Chinchali - The University of Texas at AustinUfuk Topcu - The University of Texas at Austin
- Resource Type
- Preprint
- Publication Details
- arXiv.org
- DOI
- 10.48550/arxiv.2408.13376
- eISSN
- 2331-8422
- Publisher
- Cornell University; Ithaca, New York
- Language
- English
- Date posted
- 08/23/2024
- Academic Unit
- Mathematics
- Record Identifier
- 9984698938202771
Metrics
18 Record Views