LAUSR

Learning Fast Adaptation With Meta Strategy Optimization

Sign Up to like & get
recommendations!
0 Published in 2020 at "IEEE Robotics and Automation Letters"

DOI: 10.1109/lra.2020.2974685

Abstract: The ability to walk in new scenarios is a key milestone on the path toward real-world applications of legged robots. In this work, we introduce Meta Strategy Optimization, a meta-learning algorithm for training policies with… read more here.

Keywords: adaptation; fast adaptation; strategy optimization; meta strategy ... See more keywords

Curvature-Adaptive Meta-Learning for Fast Adaptation to Manifold Data

Sign Up to like & get
recommendations!
1 Published in 2022 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"

DOI: 10.1109/tpami.2022.3164894

Abstract: Meta-learning methods are shown to be effective in quickly adapting a model to novel tasks. Most existing meta-learning methods represent data and carry out fast adaptation in euclidean space. In fact, data of real-world applications… read more here.

Keywords: curvature; meta learning; manifold data; fast adaptation ... See more keywords

Learning to Learn Task-Adaptive Hyperparameters for Few-Shot Learning.

Sign Up to like & get
recommendations!
2 Published in 2023 at "IEEE transactions on pattern analysis and machine intelligence"

DOI: 10.1109/tpami.2023.3261387

Abstract: The objective of few-shot learning is to design a system that can adapt to a given task with only few examples while achieving generalization. Model-agnostic meta-learning (MAML), which has recently gained the popularity for its… read more here.

Keywords: adaptation; task adaptive; fast adaptation; task ... See more keywords