22 citations · 103 across the 26 of their papers we have counts for
31 papers
Reinforcement Learning in Categorical Cybernetics
Jules Hedges, Riu Rodríguez Sakamoto
We show that several major algorithms of reinforcement learning (RL) fit into the framework of categorical cybernetics, that is to say, parametrised bidirectional processes. We bui…
The Compositional Structure of Bayesian Inference
Dylan Braithwaite, Jules Hedges, Toby St Clere Smithe
Bayes' rule tells us how to invert a causal process in order to update our beliefs in light of new evidence. If the process is believed to have a complex compositional structure, w…
Dependent Bayesian Lenses: Categories of Bidirectional Markov Kernels with Canonical Bayesian Inversion
Dylan Braithwaite, Jules Hedges
We generalise an existing construction of Bayesian Lenses to admit lenses between pairs of objects where the backwards object is dependent on states on the forwards object (interpr…
Value Iteration is Optic Composition
Jules Hedges, Riu Rodríguez Sakamoto
Dynamic programming is a class of algorithms used to compute optimal control policies for Markov decision processes. Dynamic programming is ubiquitous in control theory, and is als…
Fibre optics
Dylan Braithwaite, Matteo Capucci, Bruno Gavranović +2
Lenses, optics and dependent lenses (or equivalently morphisms of containers, or equivalently natural transformations of polynomial functors) are all widely used in applied categor…
Composing games into complex institutions
Seth Frey, Jules Hedges, Joshua Tan +1
Game theory is used by all behavioral sciences, but its development has long centered around tools for relatively simple games and toy systems, such as the economic interpretation…