Bram Grooten
Papers
1
Total Citations
2
H-Index
1
About
Bram Grooten is a researcher at the forefront of deep reinforcement learning, with a focus on enabling autonomous systems to operate efficiently in complex, noisy environments. His work centers on dynamic sparse training and automatic noise filtering, addressing a critical challenge in robotics: how agents can selectively attend to relevant information while ignoring irrelevant sensory input. In his most-cited paper, "Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning" (2023), Grooten introduces a novel method that allows neural networks to adaptively prune unnecessary connections during training, thereby improving both learning efficiency and task performance. This approach has direct implications for household robots and other real-world agents that must navigate cluttered, unpredictable settings. Though early in his career, Grooten’s contributions have already garnered attention, with his work cited in emerging discussions on sparse training and noise robustness. His research promises to advance the development of more resilient, resource-efficient AI systems, making him a rising voice in the reinforcement learning community.
Research Focus
Key Achievements
Top Papers
- 1