Papers
5
Total Citations
300
H-Index
3
About
Dawei Feng is a leading researcher at the intersection of artificial intelligence and robotics, with a primary focus on deep reinforcement learning (RL) and its application to multi-agent systems and decision-making. His most influential work, the 2020 survey “Deep reinforcement learning: a survey,” has garnered 277 citations, establishing it as a key reference for researchers exploring RL’s role in end-to-end control, robotic manipulation, and natural language systems. Feng’s contributions extend to decentralized multi-robot exploration, where he leverages multi-agent deep RL to enable scalable, coordinated behavior without centralized control—a critical step toward real-world robotic applications. He has also advanced meta-RL by integrating generative adversarial rewards from expert knowledge, allowing models to adapt rapidly to unseen tasks. More recently, his 2023 survey on transformers in RL for decision-making underscores his continued influence in shaping how modern architectures enhance autonomous driving, gaming AI, and robotic navigation. Feng’s work bridges theoretical foundations with practical cyber-physical systems, as highlighted in his invited paper on distributed computing for robotic perception. With a career marked by high-impact surveys and innovative multi-agent frameworks, Feng is a pivotal figure in pushing RL toward robust, intelligent autonomy.
Research Focus
Key Achievements
Top Papers
- 1Deep reinforcement learning: a survey277 citations · 2020
- 2
- 3
- 4
- 5Transformer in Reinforcement Learning for Decision-Making: A Survey2 citations · 2023