Related papers: Dynamics-Aware Quality-Diversity for Efficient Lea…

Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation-based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their…

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…

Data augmentation (DA) is a crucial technique for enhancing the sample efficiency of visual reinforcement learning (RL) algorithms. Notably, employing simple observation transformations alone can yield outstanding performance without extra…

Model-free reinforcement learning has been successfully applied to a range of challenging problems, and has recently been extended to handle large neural network policies and value functions. However, the sample complexity of model-free…

Quality-Diversity (QD) algorithms are designed to generate collections of high-performing solutions while maximizing their diversity in a given descriptor space. However, in the presence of unpredictable noise, the fitness and descriptor of…

Complex system design problems, such as those involved in aerospace engineering, require the use of numerically costly simulation codes in order to predict the performance of the system to be designed. In this context, these codes are often…

Quality-Diversity algorithms have transformed optimization by prioritizing the discovery of diverse, high-performing solutions over a single optimal result. However, traditional Quality-Diversity methods, such as MAP-Elites, rely heavily on…

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…

Quantization and Knowledge distillation (KD) methods are widely used to reduce memory and power consumption of deep neural networks (DNNs), especially for resource-constrained edge devices. Although their combination is quite promising to…

We introduce a novel Deep Reinforcement Learning (DRL) algorithm called Deep Quality-Value (DQV) Learning. DQV uses temporal-difference learning to train a Value neural network and uses this network for training a second Quality-value…

Quality-Diversity (QD) algorithms, and MAP-Elites (ME) in particular, have proven very useful for a broad range of applications including enabling real robots to recover quickly from joint damage, solving strongly deceptive maze tasks or…

Quadratic discriminant analysis (QDA) is a standard tool for classification due to its simplicity and flexibility. Because the number of its parameters scales quadratically with the number of the variables, QDA is not practical, however,…

Autonomous skill discovery aims to enable robots to acquire diverse behaviors without explicit supervision. Learning such behaviors directly on physical hardware remains challenging due to safety and data efficiency constraints. Existing…

Generating instances of different properties is key to algorithm selection methods that differentiate between the performance of different solvers for a given combinatorial optimization problem. A wide range of methods using evolutionary…

This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving the effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed framework that extends the Dyna-Q algorithm to integrate planning for task-completion…

The optimization of functions to find the best solution according to one or several objectives has a central role in many engineering and research fields. Recently, a new family of optimization algorithms, named Quality-Diversity…

In recent years, large amounts of effort have been put into pushing forward the real-world application of dynamic digital human (DDH). However, most current quality assessment research focuses on evaluating static 3D models and usually…

Deep Q-learning Network (DQN) is a successful way which combines reinforcement learning with deep neural networks and leads to a widespread application of reinforcement learning. One challenging problem when applying DQN or other…

During the last two decades, various models have been proposed for fish collective motion. These models are mainly developed to decipher the biological mechanisms of social interaction between animals. They consider very simple homogeneous…

In Evolutionary Robotics a population of solutions is evolved to optimize robots that solve a given task. However, in traditional Evolutionary Algorithms, the population of solutions tends to converge to local optima when the problem is…