Related papers: Dynamics-Aware Quality-Diversity for Efficient Lea…
The quality of data driven learning algorithms scales significantly with the quality of data available. One of the most straight-forward ways to generate good data is to sample or explore the data source intelligently. Smart sampling can…
Digital sound synthesis presents the opportunity to explore vast parameter spaces containing millions of configurations. Quality diversity (QD) evolutionary algorithms offer a promising approach to harness this potential, yet their success…
Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student model aligns its output distribution to that of a selected…
QDax is an open-source library with a streamlined and modular API for Quality-Diversity (QD) optimization algorithms in Jax. The library serves as a versatile tool for optimization purposes, ranging from black-box optimization to continuous…
Conventionally, model-based reinforcement learning (MBRL) aims to learn a global model for the dynamics of the environment. A good model can potentially enable planning algorithms to generate a large variety of behaviors and solve diverse…
Mixed-precision quantization mostly predetermines the model bit-width settings before actual training due to the non-differential bit-width sampling process, obtaining sub-optimal performance. Worse still, the conventional static…
Adaptation capabilities, like damage recovery, are crucial for the deployment of robots in complex environments. Several works have demonstrated that using repertoires of pre-trained skills can enable robots to adapt to unforeseen…
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…
Recent advances in AI have led to significant results in robotic learning, but skills like grasping remain partially solved. Many recent works exploit synthetic grasping datasets to learn to grasp unknown objects. However, those datasets…
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…
Soft robotics aims to develop robots able to adapt their behavior across a wide range of unstructured and unknown environments. A critical challenge of soft robotic control is that nonlinear dynamics often result in complex behaviors hard…
Quality-Diversity (QD) is a concept from Neuroevolution with some intriguing applications to Reinforcement Learning. It facilitates learning a population of agents where each member is optimized to simultaneously accumulate high…
Knowledge distillation (KD) has enabled remarkable progress in model compression and knowledge transfer. However, KD requires a large volume of original data or their representation statistics that are not usually available in practice.…
We utilize machine learning models which are based on recurrent neural networks to optimize dynamical decoupling (DD) sequences. DD is a relatively simple technique for suppressing the errors in quantum memory for certain noise models. In…
Quantizing deep convolutional neural networks for image super-resolution substantially reduces their computational costs. However, existing works either suffer from a severe performance drop in ultra-low precision of 4 or lower bit-widths,…
Quality-Diversity (QD) algorithms are a recent type of optimisation methods that search for a collection of both diverse and high performing solutions. They can be used to effectively explore a target problem according to features defined…
Vision-Language-Action models (VLAs) have demonstrated strong potential for embodied AI, yet their deployment on resource-limited robots remains challenging due to high memory and computational demands. While Post-Training Quantization…
Quality diversity (QD) optimization searches for a collection of solutions that optimize an objective while attaining diverse outputs of a user-specified, vector-valued measure function. Contemporary QD algorithms are typically limited to…
Training task-completion dialogue agents with reinforcement learning usually requires a large number of real user experiences. The Dyna-Q algorithm extends Q-learning by integrating a world model, and thus can effectively boost training…
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…