Skip to content

This repository includes the code for the paper: Learning, Planning, and Control in a Monolithic Neural Event Inference Architecture. Authors: Martin V. Butz, David Bilkey, Dania Humaidan, Alistair Knott and Sebastian Otte.

Notifications You must be signed in to change notification settings

CognitiveModeling/2019-ModeInferencePaperCode

Repository files navigation

Learning, Planning, and Control in a Monolithic Neural Event Inference Architecture

This repository includes the code for the paper: Learning, Planning, and Control in a Monolithic Neural Event Inference Architecture. Authors: Martin V. Butz, David Bilkey, Dania Humaidan, Alistair Knott and Sebastian Otte.

The project is structured as following:

The main class is RNNEval_CIEBdetection_MultiProblem.java, where an instance of the class ANN3InputComplexNet.java is created. The type of the used complex network is LSTM: ANNLayer_LSTM.java that implements the interface ANNLayer.java.

The used simulator is RB3Simulator.java that implements CSCProblemAndOutInMapInterface.java which in turn extends ContinuousSequentialControlProblem.java.

The required activation functions and other tools are located in de/cogmod/utilities.

In case of questions, please reach Dania Humaidan at [email protected]

Hava a look at our YouTube video of REPRISE controlling multiple vehicles and transporting objects in a goal-directed (anticipatory, active-inference-based) manner: https://www.youtube.com/watch?v=KDK94qOaaTE&t=7s

About

This repository includes the code for the paper: Learning, Planning, and Control in a Monolithic Neural Event Inference Architecture. Authors: Martin V. Butz, David Bilkey, Dania Humaidan, Alistair Knott and Sebastian Otte.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •  

Languages