The Novelty Search (NS) algorithm was proposed more than a decade ago.
H...
Learning optimal policies in sparse rewards settings is difficult as the...
Not having access to compact and meaningful representations is known to
...
In the past few years, a considerable amount of research has been dedica...
As open-ended learning based on divergent search algorithms such as Nove...
Reward-based optimization algorithms require both exploration, to find
r...
Evolvability is an important feature that impacts the ability of evoluti...
Robots are still limited to controlled conditions, that the robot design...
In a context where several policies can be observed as black boxes on
di...
Robots need to understand their environment to perform their task. If it...
To solve its task, a robot needs to have the ability to interpret its
pe...
Programming a robot to deal with open-ended tasks remains a challenge, i...
Reconstruction of the tridimensional geometry of a visual scene using th...