Tingting Pan
Papers
2
Total Citations
9
H-Index
2
About
Tingting Pan is a researcher specializing in reinforcement learning and robotic manipulation, with a focus on improving decision-making in complex, sparse-reward environments. Her work bridges artificial neural networks and robot motion planning, aiming to make autonomous systems more efficient and capable of learning from limited feedback. In her 2020 paper, "SOAR Improved Artificial Neural Network for Multistep Decision-making Tasks," she introduced a novel architecture that enhances neural network performance in sequential decision-making, earning 7 citations for its contribution to AI-driven planning. Her earlier 2018 work, "Sparse Reward Based Manipulator Motion Planning by Using High Speed Learning from Demonstrations," proposed an innovative method combining hindsight experience replay (HER) with deep deterministic policy gradient (DDPG) to accelerate learning from demonstrations. This approach addressed the challenge of sparse rewards in manipulator control, enabling faster and more reliable motion planning. Though her citation counts are modest, Pan’s research represents a meaningful step toward practical reinforcement learning applications in robotics, particularly in environments where reward signals are scarce. Her work is of interest to students and researchers exploring efficient learning algorithms for real-world robotic tasks.
Research Focus
Key Achievements
Top Papers
- 1
- 2