2 papers
cs.LG2021
Enhancing Reinforcement Learning with discrete interfaces to learn the Dyck Language
Florian Dietz, Dietrich Klakow
Even though most interfaces in the real world are discrete, no efficient way exists to train neural networks to make use of them, yet. We enhance an Interaction Network (a Reinforc…
cs.LG2020
Interaction Networks: Using a Reinforcement Learner to train other Machine Learning algorithms
Florian Dietz
The wiring of neurons in the brain is more flexible than the wiring of connections in contemporary artificial neural networks. It is possible that this extra flexibility is importa…