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

A parameterized skill is a mapping from multiple goals/task parameters to thepolicy parameters to accomplish them. Existing works in the literature show howa parameterized skill can be learned given a task space that defines all thepossible achievable goals. In this work, we focus on tasks defined in terms offinal states (goals), and we face on the challenge where the agent aims toautonomously acquire a parameterized skill to manipulate an initially unknownenvironment. In this case, the task space is not known a priori and the agenthas to autonomously discover it. The agent may posit as a task space its wholesensory space (i.e. the space of all possible sensor readings) as theachievable goals will certainly be a subset of this space. However, the spaceof achievable goals may be a very tiny subspace in relation to the wholesensory space, thus directly using the sensor space as task space exposes theagent to the curse of dimensionality and makes existing autonomous skillacquisition algorithms inefficient. In this work we present an algorithm thatactively discovers the manifold of the achievable goals within the sensorspace. We validate the algorithm by employing it in multiple differentsimulated scenarios where the agent actions achieve different types of goals:moving a redundant arm, pushing an object, and changing the color of an object.

Autonomous discovery of the goal space to learn a parameterized skill