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

5
H-Index
6
Papers
96
Total Citations
16
Avg Citations/Paper
🏆 Most Cited Paper
Accelerating Proximal Policy Optimization on CPU-FPGA Heterogeneous Platforms
46 citations · 2020
📈 Most Prolific Year: 2020 (4 Papers)
🤝 Key Collaborators: 7
🏛 Institutions: University of Southern California, Southern California University for Professional Studies

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
    QTAccel
    8 citations · 2020
  5. 5
  6. 6

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 15 days ago