Seth Siriya
Papers
1
Total Citations
3
H-Index
1
About
Seth Siriya is a researcher whose work sits at the intersection of reinforcement learning (RL) and robotics, with a particular focus on improving data efficiency in complex control tasks. His most-cited paper, "MBB: Model-Based Baseline for Efficient Reinforcement Learning" (2020), tackles a central challenge in the field: while model-free RL excels at learning policies for high-dimensional robotic systems, it often requires prohibitive amounts of data. Siriya’s contribution demonstrates how model-based approaches and optimal control can dramatically reduce sample complexity, provided an accurate system model is available. This work, with 3 citations, serves as a practical baseline for researchers seeking to bridge the gap between data-hungry model-free methods and more efficient model-based techniques. By highlighting the trade-offs between these paradigms, Siriya has helped clarify pathways toward more sample-efficient robotic learning. His research is especially relevant for students and engineers working on real-world applications where data collection is expensive or time-consuming. Through his focus on foundational efficiency challenges, Siriya contributes to making RL more viable for complex, high-stakes robotic tasks.
Research Focus
Key Achievements
Top Papers
- 1MBB: Model-Based Baseline for Efficient Reinforcement Learning.3 citations · 2020