Papers
3
Total Citations
320
H-Index
3
About
Yang Long is a leading researcher at the forefront of safe artificial intelligence, whose work is fundamentally reshaping how autonomous systems learn and operate in high-stakes environments. His primary research areas center on safe reinforcement learning (RL) and multi-agent systems, with a particular focus on ensuring that AI-driven robots and vehicles can make decisions without causing harm. Long’s most impactful contribution is his comprehensive 2024 review on safe RL, which has already garnered 194 citations, serving as a definitive guide for the field and addressing critical safety concerns in real-world deployments like autonomous driving. He further advanced the domain by pioneering safe multi-agent reinforcement learning for multi-robot control (120 citations), a breakthrough that enables fleets of robots to cooperate safely—a previously underexplored challenge. Additionally, his work on maximum entropy RL with evolution strategies tackles the stability issues of scalable learning algorithms. Through these contributions, Yang Long has established himself as a pivotal figure in creating the theoretical and practical foundations for trustworthy, real-world AI systems.
Research Focus
Key Achievements
Top Papers
- 1A Review of Safe Reinforcement Learning: Methods, Theories, and Applications194 citations · 2024
- 2Safe multi-agent reinforcement learning for multi-robot control120 citations · 2023
- 3Maximum Entropy Reinforcement Learning with Evolution Strategies6 citations · 2020