4 papers
Exploiting Dynamic and Fine-grained Semantic Scope for Extreme Multi-label Text Classification
Yuan Wang, Huiling Song, Peng Huo +4
Extreme multi-label text classification (XMTC) refers to the problem of tagging a given text with the most relevant subset of labels from a large label set. A majority of labels on…
Efficient Reuse of Previous Experiences to Improve Policies in Real Environment
Norikazu Sugimoto, Voot Tangkaratt, Thijs Wensveen +3
In this study, we show that a movement policy can be improved efficiently using the previous experiences of a real robot. Reinforcement Learning (RL) is becoming a popular approach…
Model-Based Policy Gradients with Parameter-Based Exploration by Least-Squares Conditional Density Estimation
Syogo Mori, Voot Tangkaratt, Tingting Zhao +2
The goal of reinforcement learning (RL) is to let an agent learn an optimal control policy in an unknown environment so that future expected rewards are maximized. The model-free R…
Efficient Sample Reuse in Policy Gradients with Parameter-based Exploration
Tingting Zhao, Hirotaka Hachiya, Voot Tangkaratt +2
The policy gradient approach is a flexible and powerful reinforcement learning method particularly for problems with continuous actions such as robot control. A common challenge in…