Preprint
Categorical semantics of compositional reinforcement learning
arXiv (Cornell University)
08/29/2022
DOI: 10.48550/arxiv.2208.13687
Abstract
Reinforcement learning (RL) often requires decomposing a problem into
subtasks and composing learned behaviors on these tasks. Compositionality in RL
has the potential to create modular subtask units that interface with other
system capabilities. However, generating compositional models requires the
characterization of minimal assumptions for the robustness of the compositional
feature. We develop a framework for a \emph{compositional theory} of RL using a
categorical point of view. Given the categorical representation of
compositionality, we investigate sufficient conditions under which
learning-by-parts results in the same optimal policy as learning on the whole.
In particular, our approach introduces a category $\mathsf{MDP}$, whose objects
are Markov decision processes (MDPs) acting as models of tasks. We show that
$\mathsf{MDP}$ admits natural compositional operations, such as certain fiber
products and pushouts. These operations make explicit compositional phenomena
in RL and unify existing constructions, such as puncturing hazardous states in
composite MDPs and incorporating state-action symmetry. We also model
sequential task completion by introducing the language of zig-zag diagrams that
is an immediate application of the pushout operation in $\mathsf{MDP}$.
Details
- Title: Subtitle
- Categorical semantics of compositional reinforcement learning
- Creators
- Georgios BakirtzisMichail SavvasUfuk Topcu
- Resource Type
- Preprint
- Publication Details
- arXiv (Cornell University)
- DOI
- 10.48550/arxiv.2208.13687
- eISSN
- 2331-8422
- Language
- English
- Date posted
- 08/29/2022
- Academic Unit
- Mathematics
- Record Identifier
- 9984696797702771
Metrics
1 Record Views