Nothing Special   »   [go: up one dir, main page]

×
Please click here if you are not redirected within a few seconds.
May 13, 2019 · Abstract:In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks.
The HSML aims to adapt the transferable knowledge learned from previous tasks, namely the initialization for parameters of the base learner in gradient based ...
People also ask
HSML outperforms as the soft and hierarchical clustering not only accurately captures the task relationship but also encourages knowledge transfer across ...
Source code of the paper Hierarchically Structured Meta-learning. For continual version of this algorithm, please refer to this repo.
In this paper, based on gradient-based meta-learning, we propose a hierarchically structured meta-learning (HSML) algorithm that explicitly tailors the ...
A hierarchically structured meta-learning (HSML) algorithm that explicitly tailors the transferable knowledge to different clusters of tasks, ...
Meta-learning aims to train models that can learn from a variety of related tasks and use that learned knowledge to solve new and unseen tasks more ...
We develop a metalearning approach for learning hierarchically structured policies, improving sample efficiency on unseen tasks through the use of shared ...
Abstract: We develop a metalearning approach for learning hierarchically structured poli- cies, improving sample efficiency on unseen tasks through the use ...
Building on the meta-learning of hierarchically structured policies, we further investigated how these policies were represented and how state abstractions ...