Active domain randomization
Active domain randomization is a technique used in machine learning and robotics to improve the generalization of models by introducing variability in training environments.
generalization
Overfitting
Overfitting is a modeling error in machine learning and statistics where a model captures noise or random fluctuations in training data rather than the underlying pattern. This leads to poor generalization to new, unseen data.
Learning to adapt (meta-learning for domain shift)
Learning to adapt, or meta-learning for domain shift, refers to methods in machine learning that enable models to generalize across varying domains.
Domain randomization
Domain randomization is a technique used in machine learning and robotics to improve the robustness of models by training them on a diverse set of simulated environments.
Stochastic weight averaging (SWA)
Stochastic weight averaging (SWA) is an optimization technique used in training deep neural networks. It involves averaging multiple sets of weights collected at different points during the training process to improve generalization and model performance.