Allison Pinosky
Papers
2
Total Citations
47
H-Index
2
About
Allison Pinosky is a rising researcher in robotics and artificial intelligence, specializing in reinforcement learning and control systems. Her work focuses on bridging the gap between model-based and model-free approaches to enhance robotic learning and adaptability. In her highly cited 2022 paper, "Hybrid control for combining model-based and model-free reinforcement learning" (30 citations), Pinosky introduced a novel framework that integrates learned predictive models with experience-based policy mappings. This hybrid approach allows robots to leverage both task understanding and dynamic adaptation, significantly improving learning efficiency in complex environments. Her subsequent 2024 work, "Maximum diffusion reinforcement learning" (17 citations), further advances the field by exploring exploration strategies for more robust policy learning. Pinosky's contributions are shaping how robots acquire and refine skills, with potential applications in autonomous systems and human-robot interaction. Her innovative synthesis of control theory and machine learning positions her as a key voice in next-generation robotic intelligence.
Research Focus
Key Achievements
Top Papers
- 1
- 2Maximum diffusion reinforcement learning17 citations · 2024