English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Open-ended learning is a core research field of developmental robotics and AIaiming to build learning machines and robots that can autonomously acquireknowledge and skills incrementally as infants and children. The firstcontribution of this work is to study the challenges posed by the previouslyproposed benchmark `REAL competition' aiming to foster the development of trulyopen-ended learning robot architectures. The competition involves a simulatedcamera-arm robot that: (a) in a first `intrinsic phase' acquires sensorimotorcompetence by autonomously interacting with objects; (b) in a second `extrinsicphase' is tested with tasks unknown in the intrinsic phase to measure thequality of knowledge previously acquired. This benchmark requires the solutionof multiple challenges usually tackled in isolation, in particular exploration,sparse-rewards, object learning, generalisation, task/goal self-generation, andautonomous skill learning. As a second contribution, we present a set of`REAL-X' robot architectures that are able to solve different versions of thebenchmark, where we progressively release initial simplifications. Thearchitectures are based on a planning approach that dynamically increasesabstraction, and intrinsic motivations to foster exploration. REAL-X achieves agood performance level in very demanding conditions. We argue that the REALbenchmark represents a valuable tool for studying open-ended learning in itshardest form.

REAL-X -- Robot open-Ended Autonomous Learning Architectures: Achieving Truly End-to-End Sensorimotor Autonomous Learning Systems