REAL-2019: Robot open-Ended Autonomous Learning competition

Emilio Cartoni, Francesco Mannella, Vieri Giuliano Santucci, Jochen Triesch, Elmar Rueckert, Gianluca Baldassarre
Proceedings of the NeurIPS 2019 Competition and Demonstration Track, PMLR 123:142-152, 2020.

Abstract

Open-ended learning, also called life-long learning or autonomous curriculum learning, aims to program machines and robots that autonomously acquire knowledge and skills in a cumulative fashion. We illustrate the first edition of the REAL-2019 – Robot open-Ended Autonomous Learning competition, prompted by the EU project GOAL-Robots – Goal-based Open-ended Autonomous Learning Robots. The competition was based on a simulated robot that: (a) acquires sensorimotor competence to interact with objects on a table; (b) learns autonomously based on mechanisms such as curiosity, intrinsic motivations, and self-generated goals. The competition featured a first intrinsic phase, where the robots learned to interact with the objects in a fully autonomous way (no rewards, predefined tasks or human guidance), and a second extrinsic phase, where the acquired knowledge was evaluated with tasks unknown during the first phase. The competition ran online on AIcrowd for six months, involved 75 subscribers and 6 finalists, and was presented at NeurIPS-2019. The competition revealed very hard as it involved difficult machine learning challenges usually tackled in isolation, such as exploration, sparse rewards, object learning, generalisation, catastrophic interference, and autonomous skill learning. Following the participant’s positive feedback, the preparation of a second REAL-2020 competition is underway, improving on the formulation of a relevant benchmark for open-ended learning.

Cite this Paper

BibTeX
@InProceedings{pmlr-v123-cartoni20a, title = {REAL-2019: Robot open-Ended Autonomous Learning competition}, author = {Cartoni, Emilio and Mannella, Francesco and Santucci, Vieri Giuliano and Triesch, Jochen and Rueckert, Elmar and Baldassarre, Gianluca}, booktitle = {Proceedings of the NeurIPS 2019 Competition and Demonstration Track}, pages = {142--152}, year = {2020}, editor = {Escalante, Hugo Jair and Hadsell, Raia}, volume = {123}, series = {Proceedings of Machine Learning Research}, month = {08--14 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v123/cartoni20a/cartoni20a.pdf}, url = {https://proceedings.mlr.press/v123/cartoni20a.html}, abstract = {Open-ended learning, also called life-long learning or autonomous curriculum learning, aims to program machines and robots that autonomously acquire knowledge and skills in a cumulative fashion. We illustrate the first edition of the REAL-2019 – Robot open-Ended Autonomous Learning competition, prompted by the EU project GOAL-Robots – Goal-based Open-ended Autonomous Learning Robots. The competition was based on a simulated robot that: (a) acquires sensorimotor competence to interact with objects on a table; (b) learns autonomously based on mechanisms such as curiosity, intrinsic motivations, and self-generated goals. The competition featured a first intrinsic phase, where the robots learned to interact with the objects in a fully autonomous way (no rewards, predefined tasks or human guidance), and a second extrinsic phase, where the acquired knowledge was evaluated with tasks unknown during the first phase. The competition ran online on AIcrowd for six months, involved 75 subscribers and 6 finalists, and was presented at NeurIPS-2019. The competition revealed very hard as it involved difficult machine learning challenges usually tackled in isolation, such as exploration, sparse rewards, object learning, generalisation, catastrophic interference, and autonomous skill learning. Following the participant’s positive feedback, the preparation of a second REAL-2020 competition is underway, improving on the formulation of a relevant benchmark for open-ended learning.} }
Endnote
%0 Conference Paper %T REAL-2019: Robot open-Ended Autonomous Learning competition %A Emilio Cartoni %A Francesco Mannella %A Vieri Giuliano Santucci %A Jochen Triesch %A Elmar Rueckert %A Gianluca Baldassarre %B Proceedings of the NeurIPS 2019 Competition and Demonstration Track %C Proceedings of Machine Learning Research %D 2020 %E Hugo Jair Escalante %E Raia Hadsell %F pmlr-v123-cartoni20a %I PMLR %P 142--152 %U https://proceedings.mlr.press/v123/cartoni20a.html %V 123 %X Open-ended learning, also called life-long learning or autonomous curriculum learning, aims to program machines and robots that autonomously acquire knowledge and skills in a cumulative fashion. We illustrate the first edition of the REAL-2019 – Robot open-Ended Autonomous Learning competition, prompted by the EU project GOAL-Robots – Goal-based Open-ended Autonomous Learning Robots. The competition was based on a simulated robot that: (a) acquires sensorimotor competence to interact with objects on a table; (b) learns autonomously based on mechanisms such as curiosity, intrinsic motivations, and self-generated goals. The competition featured a first intrinsic phase, where the robots learned to interact with the objects in a fully autonomous way (no rewards, predefined tasks or human guidance), and a second extrinsic phase, where the acquired knowledge was evaluated with tasks unknown during the first phase. The competition ran online on AIcrowd for six months, involved 75 subscribers and 6 finalists, and was presented at NeurIPS-2019. The competition revealed very hard as it involved difficult machine learning challenges usually tackled in isolation, such as exploration, sparse rewards, object learning, generalisation, catastrophic interference, and autonomous skill learning. Following the participant’s positive feedback, the preparation of a second REAL-2020 competition is underway, improving on the formulation of a relevant benchmark for open-ended learning.
APA
Cartoni, E., Mannella, F., Santucci, V.G., Triesch, J., Rueckert, E. & Baldassarre, G.. (2020). REAL-2019: Robot open-Ended Autonomous Learning competition. Proceedings of the NeurIPS 2019 Competition and Demonstration Track, in Proceedings of Machine Learning Research 123:142-152 Available from https://proceedings.mlr.press/v123/cartoni20a.html.

Related Material