activity
20172023
most citedAlphaStar: An Evolutionary Computation Perspective

124 citations · 350 across the 23 of their papers we have counts for

collaborators
Showing cs.ROShow all

6 papers · 1 filter

cs.RO20231 cited

Quality-Diversity Optimisation on a Physical Robot Through Dynamics-Aware and Reset-Free Learning

Simón C. Smith, Bryan Lim, Hannah Janmohamed +1

Learning algorithms, like Quality-Diversity (QD), can be used to acquire repertoires of diverse robotics skills. This learning is commonly done via computer simulation due to the l…

cs.RO2022

Online Damage Recovery for Physical Robots with Hierarchical Quality-Diversity

Maxime Allard, Simón C. Smith, Konstantinos Chatzilygeroudis +2

In real-world environments, robots need to be resilient to damages and robust to unforeseen scenarios. Quality-Diversity (QD) algorithms have been successfully used to make robots…

cs.RO202212 cited

Hierarchical Quality-Diversity for Online Damage Recovery

Maxime Allard, Simón C. Smith, Konstantinos Chatzilygeroudis +1

Adaptation capabilities, like damage recovery, are crucial for the deployment of robots in complex environments. Several works have demonstrated that using repertoires of pre-train…

cs.RO2019

Multimodal representation models for prediction and control from partial information

Martina Zambelli, Antoine Cully, Yiannis Demiris

Similar to humans, robots benefit from interacting with their environment through a number of different sensor modalities, such as vision, touch, sound. However, learning from diff…

cs.RO201968 cited

Autonomous skill discovery with Quality-Diversity and Unsupervised Descriptors

Antoine Cully

Quality-Diversity optimization is a new family of optimization algorithms that, instead of searching for a single optimal solution to solving a task, searches for a large collectio…

cs.RO2018

Hierarchical Behavioral Repertoires with Unsupervised Descriptors

Antoine Cully, Yiannis Demiris

Enabling artificial agents to automatically learn complex, versatile and high-performing behaviors is a long-lasting challenge. This paper presents a step in this direction with hi…