Optimal Frame RTB Algorithm Using Deep Reinforcement Learning

Last updated on Mar 24, 2026

Technical Lead | CNAI, KAIST | Mar. 2020–Mar. 2021

  • Independently formulated the optimization problem for customized real-time bidding of online ad frames as a Markov decision process.
  • Designed an offline deep reinforcement learning method based on counterfactual learning to address the data scarcity inherent in the target settings.
  • Led a team of engineers and researchers from algorithm design through software implementation and delivery.
Reinforcement Learning
Myoung Hoon Ha
Myoung Hoon Ha
Postdoctoral Researcher

My research focuses on neuroscience-inspired AI, with particular emphasis on predictive coding, iterative inference, and stable learning in deep architectures.