REAL-2019: Robot open-Ended Autonomous Learning competition

Emilio Cartoni Francesco Mannella Vieri Giuliano Santucci Jochen Triesch
Elmar Rueckert Gianluca Baldassarre


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 โ€“ Robot open-Ended Autonomous Learning competition, prompted by the EU project GOAL-Robots โ€“ 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 participantโ€™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.

Back to AIcrowd Research