Generating Natural Behaviors using Constructivist Algorithms

Olivier L. Georgeon, Paul Robertson, Jianyong Xue
Proceedings of the First International Workshop on Self-Supervised Learning, PMLR 131:5-14, 2020.

Abstract

We present a project to design interactive devices (smart displays, robots, etc.) capable of self-motivated learning through non-goal-directed interactive behaviors (e.g., curious, emotional, playful behaviors). We use and improve algorithms inspired by constructivist epistemology that we have designed previously. These algorithms incrementally learn se- quential hierarchies of control loops in a bottom-up and open-ended fashion, and continu- ously reuse the learned higher-level control loops to generate increasingly complex behaviors that exhibit self-motivation. This project contributes to research in self-supervised learning because the learning is driven by low-level preferences that under-determine the device’s fu- ture behaviors, leaving room for individuation, which, in turn, opens the way to autonomy in learning.

Cite this Paper

BibTeX
@InProceedings{pmlr-v131-georgeon20a, title = {Generating Natural Behaviors using Constructivist Algorithms}, author = {Georgeon, Olivier L. and Robertson, Paul and Xue, Jianyong}, booktitle = {Proceedings of the First International Workshop on Self-Supervised Learning}, pages = {5--14}, year = {2020}, editor = {Minsky, Henry and Robertson, Paul and Georgeon, Olivier L. and Minsky, Milan and Shaoul, Cyrus}, volume = {131}, series = {Proceedings of Machine Learning Research}, month = {27--28 Feb}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v131/georgeon20a/georgeon20a.pdf}, url = {https://proceedings.mlr.press/v131/georgeon20a.html}, abstract = {We present a project to design interactive devices (smart displays, robots, etc.) capable of self-motivated learning through non-goal-directed interactive behaviors (e.g., curious, emotional, playful behaviors). We use and improve algorithms inspired by constructivist epistemology that we have designed previously. These algorithms incrementally learn se- quential hierarchies of control loops in a bottom-up and open-ended fashion, and continu- ously reuse the learned higher-level control loops to generate increasingly complex behaviors that exhibit self-motivation. This project contributes to research in self-supervised learning because the learning is driven by low-level preferences that under-determine the device’s fu- ture behaviors, leaving room for individuation, which, in turn, opens the way to autonomy in learning.} }
Endnote
%0 Conference Paper %T Generating Natural Behaviors using Constructivist Algorithms %A Olivier L. Georgeon %A Paul Robertson %A Jianyong Xue %B Proceedings of the First International Workshop on Self-Supervised Learning %C Proceedings of Machine Learning Research %D 2020 %E Henry Minsky %E Paul Robertson %E Olivier L. Georgeon %E Milan Minsky %E Cyrus Shaoul %F pmlr-v131-georgeon20a %I PMLR %P 5--14 %U https://proceedings.mlr.press/v131/georgeon20a.html %V 131 %X We present a project to design interactive devices (smart displays, robots, etc.) capable of self-motivated learning through non-goal-directed interactive behaviors (e.g., curious, emotional, playful behaviors). We use and improve algorithms inspired by constructivist epistemology that we have designed previously. These algorithms incrementally learn se- quential hierarchies of control loops in a bottom-up and open-ended fashion, and continu- ously reuse the learned higher-level control loops to generate increasingly complex behaviors that exhibit self-motivation. This project contributes to research in self-supervised learning because the learning is driven by low-level preferences that under-determine the device’s fu- ture behaviors, leaving room for individuation, which, in turn, opens the way to autonomy in learning.
APA
Georgeon, O.L., Robertson, P. & Xue, J.. (2020). Generating Natural Behaviors using Constructivist Algorithms. Proceedings of the First International Workshop on Self-Supervised Learning, in Proceedings of Machine Learning Research 131:5-14 Available from https://proceedings.mlr.press/v131/georgeon20a.html.

Related Material