Policy Reuse for Dialog Management Using Action-Relation Probability
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Access"
DOI: 10.1109/access.2020.3017780
Abstract: We study the problem of policy adaptation for reinforcement-learning-based dialog management. Policy adaptation is a commonly used technique to alleviate the problem of data sparsity when training a goal-oriented dialog system for a new task… read more here.
Keywords: target task; policy; task; dialog management ... See more keywords
Learning Rates of Regularized Regression With Multiple Gaussian Kernels for Multi-Task Learning
Sign Up to like & getrecommendations! Published in 2018 at "IEEE Transactions on Neural Networks and Learning Systems"
DOI: 10.1109/tnnls.2018.2802469
Abstract: This paper considers a least square regularized regression algorithm for multi-task learning in a union of reproducing kernel Hilbert spaces (RKHSs) with Gaussian kernels. It is assumed that the optimal prediction function of the target… read more here.
Keywords: multi task; task; target task; task learning ... See more keywords