Enhancing Reinforcement Learning with discrete interfaces to learn the Dyck Language

no code implementations • 27 Oct 2021 • 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.

reinforcement-learning Reinforcement Learning (RL)

Interaction Networks: Using a Reinforcement Learner to train other Machine Learning algorithms

no code implementations • 15 Jun 2020 • Florian Dietz

An Interaction Network consists of a collection of conventional neural networks, a set of memory locations, and a DQN or other reinforcement learner.

BIG-bench Machine Learning Decision Making