Carson Eisenach
Papers
1
Total Citations
5
H-Index
1
About
Carson Eisenach is a researcher working at the intersection of reinforcement learning and decision-making under uncertainty, with a particular focus on policy optimization in complex, structured action spaces. His most notable contribution, "Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications" (2018), addresses a fundamental challenge in modern reinforcement learning: how agents can effectively learn continuous control policies in domains where actions are bounded or hierarchically structured, such as robotics control and real-time strategy games. By developing a unified family of gradient estimators, Eisenach's work bridges the gap between purely continuous and discrete-continuous hybrid action spaces, offering practitioners more principled and flexible tools for policy optimization. This contribution has attracted citations from researchers working across robotics, game-playing agents, and theoretical reinforcement learning, reflecting its broad methodological relevance. His research speaks directly to the growing demand for scalable, mathematically rigorous approaches to sequential decision-making in high-dimensional environments, making his work particularly valuable to students and practitioners seeking to apply reinforcement learning to real-world control problems where standard policy gradient methods fall short.
Research Focus
Key Achievements
Top Papers
- 1