Sanmukh R. Kuppannagari
University of Southern California, Southern California University for Professional Studies
Papers
6
Total Citations
96
H-Index
5
About
Sanmukh R. Kuppannagari is a computer systems researcher specializing in hardware acceleration for artificial intelligence, with a particular focus on reinforcement learning (RL) on heterogeneous computing platforms. His work sits at the intersection of machine learning algorithms and high-performance computing, addressing one of the most pressing challenges in modern AI: making RL training faster and more efficient. Kuppannagari's most impactful contribution is his pioneering work on FPGA-based acceleration of state-of-the-art RL algorithms. His 2020 paper on accelerating Proximal Policy Optimization (PPO) on CPU-FPGA heterogeneous platforms has garnered 46 citations, establishing him as a leading voice in hardware-accelerated RL. This work, alongside his QTAccel framework for Q-Table-based RL accelerators (19 citations), demonstrates his ability to translate algorithmic innovation into tangible hardware solutions. His subsequent PPOAccel framework further refined high-throughput RL training pipelines. Beyond hardware design, Kuppannagari has investigated scalable parallel training paradigms and systematically characterized deep RL performance across heterogeneous platforms, providing the research community with valuable benchmarking insights. Collectively, his publications offer both theoretical grounding and practical tools that help researchers and engineers deploy RL systems more efficiently across robotics, gaming, and autonomous systems applications.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4QTAccel8 citations · 2020
- 5
- 6