Related papers: Model-Based Quality-Diversity Search for Efficient…
We present a Quality-Diversity benchmark suite for Deep Neuroevolution in Reinforcement Learning domains for robot control. The suite includes the definition of tasks, environments, behavioral descriptors, and fitness. We specify different…
Deep Reinforcement Learning (RL) has emerged as a powerful paradigm for training neural policies to solve complex control tasks. However, these policies tend to be overfit to the exact specifications of the task and environment they were…
Consider the problem of training robustly capable agents. One approach is to generate a diverse collection of agent polices. Training can then be viewed as a quality diversity (QD) optimization problem, where we search for a collection of…
This paper introduces a user-driven evolutionary algorithm based on Quality Diversity (QD) search. During a design session, the user iteratively selects among presented alternatives and their selections affect the upcoming results. We aim…
Improving open-ended learning capabilities is a promising approach to enable robots to face the unbounded complexity of the real-world. Among existing methods, the ability of Quality-Diversity algorithms to generate large collections of…
Quality-Diversity algorithms are powerful tools for discovering diverse, high-performing solutions. Recently, Multi-Objective Quality-Diversity (MOQD) extends QD to problems with several objectives while preserving solution diversity. MOQD…
Quality-Diversity (QD) algorithms aim to discover diverse, high-performing solutions across behavioral niches. However, QD search often stagnates as incremental variation operators struggle to propagate building blocks across large…
Traditional optimization algorithms search for a single global optimum that maximizes (or minimizes) the objective function. Multimodal optimization algorithms search for the highest peaks in the search space that can be more than one.…
Quality-Diversity optimisation algorithms enable the evolution of collections of both high-performing and diverse solutions. These collections offer the possibility to quickly adapt and switch from one solution to another in case it is not…
In contrast to humans and animals who naturally execute seamless motions, learning and smoothly executing sequences of actions remains a challenge in robotics. This paper introduces a novel skill-agnostic framework that learns to sequence…
Quality Diversity (QD) algorithms have been proposed to search for a large collection of both diverse and high-performing solutions instead of a single set of local optima. While early QD algorithms view the objective and descriptor…
In this work, we consider the problem of Quality-Diversity (QD) optimization with multiple objectives. QD algorithms have been proposed to search for a large collection of both diverse and high-performing solutions instead of a single set…
In the context of neuroevolution, Quality-Diversity algorithms have proven effective in generating repertoires of diverse and efficient policies by relying on the definition of a behavior space. A natural goal induced by the creation of…
While the field of Quality-Diversity (QD) has grown into a distinct branch of stochastic optimization, a few problems, in particular locomotion and navigation tasks, have become de facto standards. Are such benchmarks sufficient? Are they…
Quality-Diversity optimisation (QD) has proven to yield promising results across a broad set of applications. However, QD approaches struggle in the presence of uncertainty in the environment, as it impacts their ability to quantify the…
Quality diversity (QD) algorithms have shown to provide sets of high quality solutions for challenging problems in robotics, games, and combinatorial optimisation. So far, theoretical foundational explaining their good behaviour in practice…
The Reinforcement Learning field is strong on achievements and weak on reapplication; a computer playing GO at a super-human level is still terrible at Tic-Tac-Toe. This paper asks whether the method of training networks improves their…
Recent works have shown that by curating high quality and diverse instruction tuning datasets, we can significantly improve instruction-following capabilities. However, creating such datasets is difficult and most works rely on manual…
Quality diversity (QD) is a branch of evolutionary computation that seeks high-quality and behaviorally diverse solutions to a problem. While adversarial problems are common, classical QD cannot be easily applied to them, as both the…
With the development of fast and massively parallel evaluations in many domains, Quality-Diversity (QD) algorithms, that already proved promising in a large range of applications, have seen their potential multiplied. However, we have yet…