Dongfang Zhao

Beijing Technology and Business University

Papers

1

Total Citations

5

H-Index

1

About

Dongfang Zhao is a researcher at the forefront of reinforcement learning and autonomous robotics, with a particular focus on enhancing sample efficiency in continuous action spaces. His most-cited work, "Active Exploration Deep Reinforcement Learning for Continuous Action Space with Forward Prediction" (2024), introduces a novel framework that leverages forward prediction models to guide exploration, enabling agents to extract maximal knowledge from limited environmental interactions. This contribution directly addresses a critical bottleneck in deploying RL to real-world robotics, where data collection is costly and time-consuming. With 5 citations already in a short span, Zhao’s research is gaining traction for its practical implications in improving learning speed and autonomy. His work stands out for bridging deep RL with predictive modeling, offering a pathway to more intelligent and adaptive robotic systems. Zhao’s achievements reflect a commitment to advancing AI-driven robotics, making him a promising voice in the field of sample-efficient learning and autonomous decision-making.

Research Focus

Key Achievements

1
H-Index
1
Papers
5
Total Citations
5
Avg Citations/Paper
🏆 Most Cited Paper
Active Exploration Deep Reinforcement Learning for Continuous Action Space with Forward Prediction
5 citations · 2024
📈 Most Prolific Year: 2024 (1 Papers)
🤝 Key Collaborators: 1
🏛 Institutions: Beijing Technology and Business University

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago