Search Results for author:
Found 6 papers, 5 papers with code
QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration
QDax is an open-source library with a streamlined and modular API for Quality-Diversity (QD) optimization algorithms in Jax.
Benchmarking Quality-Diversity Algorithms on Neuroevolution for Reinforcement Learning
We present a Quality-Diversity benchmark suite for Deep Neuroevolution in Reinforcement Learning domains for robot control.
Online Damage Recovery for Physical Robots with Hierarchical Quality-Diversity
Quality-Diversity (QD) algorithms have been successfully used to make robots adapt to damages in seconds by leveraging a diverse set of learned skills.
Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery
Recent work has shown that training a mixture of policies, as opposed to a single one, that are driven to explore different regions of the state-action space can address this shortcoming by generating a diverse set of behaviors, referred to as skills, that can be collectively used to great effect in adaptation tasks or for hierarchical planning.
Hierarchical Quality-Diversity for Online Damage Recovery
These adaptation capabilities are directly linked to the behavioural diversity in the repertoire.
Accelerated Quality-Diversity through Massive Parallelism
With recent advances in simulators that run on accelerators, thousands of evaluations can now be performed in parallel on single GPU/TPU.
