Andrea Rafanelli
Papers
1
Total Citations
4
H-Index
1
About
Andrea Rafanelli is a researcher at the intersection of artificial intelligence, robotics, and procedural content generation, with a primary focus on advancing deep reinforcement learning (RL) for autonomous systems. Her most cited work, "Extension of constraint-procedural logic-generated environments for deep Q-learning agent training and benchmarking" (2023), introduces a novel framework that uses constraint-procedural logic to automatically generate diverse, complex training environments for deep Q-learning agents. This contribution addresses a critical bottleneck in RL: the need for varied, realistic scenarios to prevent overfitting and improve agent generalization. By enabling the systematic creation of benchmark environments, Rafanelli’s work provides a scalable tool for training robots to explore unknown spaces, detect objects, and perform tasks with greater robustness. Her research has garnered attention for its practical implications in autonomous exploration and task execution, earning citations from peers seeking to enhance RL training pipelines. Rafanelli’s approach stands out for bridging procedural generation with constraint-based logic, offering a structured yet flexible method to simulate real-world challenges. Her ongoing work continues to shape how researchers design and evaluate learning agents for dynamic environments, making her a notable voice in the push toward more adaptable, intelligent robotics.
Research Focus
Key Achievements
Top Papers
- 1