#+html:

AlgebraicRL.jl Compositional reinforcement learning.

=AlgebraicRL.jl= is a Julia library for composing Markov decision processes (MDPs) and their agents compositionally. The library implements algebras for compositional reinforcement learning assisted by [[https://github.com/AlgebraicJulia/Catlab.jl][Catlab.jl]] to build a computational interpretation of the categorical semantics that make composition formally precise. The [[https://bakirtzisg.github.io/AlgebraicRL.jl/dev/][documentation]] describes the process to compose unit MDPs.