Voot Tangkaratt

关于

暂无简介。

研究焦点

主要成就

代表论文

1. 1
   Efficient Sample Reuse in Policy Gradients with Parameter-Based Exploration

   27 次引用 · 2013
2. 2
   Discovering diverse solutions in deep reinforcement learning by maximizing state–action-based mutual information

   21 次引用 · 2022
3. 3
   Model-based reinforcement learning with dimension reduction

   14 次引用 · 2016
4. 4
   Conditional Density Estimation with Dimensionality Reduction via Squared-Loss Conditional Entropy Minimization

   13 次引用 · 2014
5. 5
   Simultaneous Planning for Item Picking and Placing by Deep Reinforcement Learning

   12 次引用 · 2020
6. 6
   Direct conditional probability density estimation with sparse feature selection

   10 次引用 · 2015
7. 7
   Trial and Error: Using Previous Experiences as Simulation Models in Humanoid Motor Learning

   6 次引用 · 2016
8. 8
   Efficient reuse of previous experiences in humanoid motor learning

   4 次引用 · 2014

主要合作者