Steven Carr
Papers
1
Total Citations
6
H-Index
1
About
Steven Carr is a researcher at the forefront of safe multi-agent decision-making under uncertainty, with a focus on bridging the gap between theoretical guarantees and practical deployment. His work centers on planning in complex, partially observable environments where an autonomous agent must not only maximize performance but also adhere to strict safety constraints, even in the presence of adversarial or uncontrollable actors. In his highly cited 2021 paper, "Safe Policies for Factored Partially Observable Stochastic Games," Carr introduced a novel framework for multi-objective planning that explicitly separates reward maximization from safety specification, offering provable safety guarantees in adversarial settings. This work has garnered 6 citations and has laid the groundwork for subsequent advances in risk-aware planning. Carr’s research is particularly impactful for applications in robotics, autonomous driving, and human-robot interaction, where ensuring safe behavior is paramount. His contributions are helping to shape a new generation of algorithms that are both theoretically sound and practically viable, making him a rising voice in the fields of safe reinforcement learning and game-theoretic planning.
Research Focus
Key Achievements
Top Papers
- 1Safe Policies for Factored Partially Observable Stochastic Games6 citations · 2021