Test…

• 리니지 리마스터 잊혀진 섬 용병 2022-01 ~ 2023-12
  • 플레이어의 명령에 따라 다양한 행동을 보일 수 있는 RL agent 학습기술 개발
• 리니지 리마스터 거울전쟁 2021-01 ~ 2021-12
  • 리니지 PC (리마스터)환경에서 강화학습 AI가 직접 학습하기 어려운 장거리 이동을 처리할 수 있는 플레이어 매니저 AI 구현
  • 리니지 PC 환경에서 python 코드부분을 최적화
• StarCraft II 환경에서 다양한 플레이 스타일 학습 실험 2019-01 ~ 2020-02
  • PBT와 QD (MAP-Elites)를 결합
• StarCraft II AI 연구 2018-10-2018-12
  • 공개된 StarCraft II 플랫폼을 이용해서 Game AI를 위한 강화학습 등 기계학습 기술을 연구/개발
  • 플랫폼의 특성을 파악하고 관련된 최신기술을 조사 및 실험
• NC Fellowship 경진대회 플랫폼/예제 개발 2018-01 ~ 2018-12
  • 학부생을 대상으로한 Game AI 개발 경진대회에서 사용할 플랫폼과 예제 개발
  • 미니 체스의 일종인 마이크로 체스를 기반으로 플랫폼 개발하고, AlphaGo와 유사한 MCTS를 사용하는 self-play learning 예제 구현
• Maestro 2015-07 ~ 2016-06
  • 모바일 RTS게임 개발프로젝트
  • 화면이 작고 조작이 어려운 모바일 환경에서 RTS 게임을 수월하게 플레이 할 수 있도록 플레이어를 보조해주는 부관 AI를 만드는 업무 수행

• M.-J. Kim, H.-S. Park, and C.-W. Ahn, “Nondominated Policy-Guided Learning in Multi-Objective Reinforcement Learning.” Electronics, 11.7, MDPI, 2022.

• H.-S. Park, and K.-J. Kim, “Automatic Learning Rate Adjustment for Deep Reinforcement Learning using Evolutionary Algorithm on Multiple Machines,” VGML (Video Games and Machine Learning) workshop @ICML2017. (accepted)

• H.-S. Park, and K.-J. Kim, “Deep Q-Learning using Redundant Outputs in Visual Doom”, IEEE Conference on Computational Intelligence and Games, 2016.
• H.-S. Park and K.-J. Kim, “Active Player Modeling in the Iterated Prisoner's Dilemma,” Computational Intelligence and Neuroscience, 2016 Link.
• H.-C. Cho, H.-S. Park, C.-Y. Kim and K.-J. Kim, “Investigation of the Effect of “Fog of War” in the Prediction of StarCraft Strategy Using Machine Learning.” Computers in Entertainment (CIE), ACM Computers in Entertainment (CIE), vol. 14.1, no.2, 2016.

• H.-S. Park, and K.-J. Kim, “MCTS with Influence Map for General Video Game Playing,” IEEE Conference on Computational Intelligence and Games, 2015.(pp.534-535)
• H.-S. Park, H.-T. Kim, and K.-J. Kim, “GreedyUCB1 based Monte-Carlo Tree Search for General Video Game Playing Artificial Intelligence,” KIISE Transactions on Computing Practices, vol. 21, no. 8, pp. 572-577, Aug 2015.
• M. Swiechowski, H.-S. Park, J. Mańdziuk and K.-J. Kim,“Recent Advances in General Game Playing,” The Scientific World Journal, 2015.

• S. S. Farooq, H.-S. Park, and K.-J. Kim, “Inference of Opponent's Uncertain States in Ghost Game using Machine Learning,” The 18th Asia Pacific Symposium on Intelligent and Evolutionary Systems, 2014 (pp. 335-346)
• H.-S. Park, and K.-J. Kim, “Social Network Analysis of High-Level Players in Multiplayer Online Battle Arena Game,” The First Exploration on Games and Gamers Workshop @ SocInfo 2014.
• H.-S. Park and K.-J. Kim, “Learning to Play Fighting Game using Massive Play Data,” IEEE Conference on Computational Intelligence and Games, 2014.

• H.-S. Park, and K.-J. Kim, “Opponents modeling with incremental active learning: A case study of iterative prisoner's dilemma,” IEEE Conference on Computational Intelligence in Games, 2013.
• H.-S. Park and K.-J. Kim, “Active Data Collection and Opponent Player Modeling using Estimation-Exploration Algorithm and Evolutionary Neural Network,” KIISE Fall Conference, 2013.
• H.-S. Park, D.-M. Yoon, H.-C. Cho, and K.-J. Kim, “Applications of machine learning for games: Case studies,” IEEK Summer Conference, 2013.
• H.-S. Park and K.-J. Kim, “Opponent's player's decision modeling in iterated prisoner's dilemma using reverse engineering technique,” Korea Congress on Computer, 2013.
• H.-S. Park, and K.-J. Kim, “Recent Research Trends in Game Artificial Intelligence,” Communications of the Korean Institute of Information Scientists and Engineers, July 2013.
• H.-S. Park, and K.-J. Kim, “The Automated Fault-Recovery for Four-Legged Robots using Parallel Genetic Algorithm,” Procedia Computer Science, pp. 158-166, 2013.
• J.-E. Lee, H.-S. Park, K.-J. Kim and J.-C. No, “Learning to Predict the Need of Summarization on News Articles,” Procedia Computer Science, pp. 274-279, 2013.

• H.-S. Park, H.-C. Cho, K.-Y. Lee, and K.-J. Kim, “Prediction of early stage opponent strategy for StarCraft AI using scouting and machine learning,” Workshop at SIGGRAPH ASIA (Computer Gaming Track), pp. 7-12, 2012.
• H.-S. Park and K.-J. Kim, “Automatic python programming using stack-based genetic programming,” Genetic and Evolutionary Computation Conference (GECCO), pp. 641-642, 2012.
• H.-S. Park and K.-J. Kim, “Evolving a neural controller for fault-tolerant four-legged robots using parallel genetic algorithm,” International Conference on Advanced Information Technology and Sensor Application, p. 129, 2012.
• H.-S. Park, and K.-J. Kim, “Python bytecode evolution using stack-based genetic programming for regression problems,” Symposium on Brain and Artificial Intelligence, 2012 (Abstract).
• H.-S. Park, A.-R. Park and K.-J. Kim, “Fault-tolerant analog circuit design using average and worst case analysis evolutionary strategy,” Korea Congress on Computer 2012.

• H.-S. Park and K.-J. Kim, “Automated synthesis of physically implementable analog circuits using evolutionary strategy and practical constraints on component values,” Journal of KIISE: Software and Applications, vol. 38, no. 5, pp. 248-256, 2011.
• H.-S. Park, and K.-J. Kim, “Genetic Programming using Bytecode-Level Evolution for Python Programming Language,” KIISE Fall Conference, 2011.
• H.-S. Park, and K.-J. Kim, “Research on scalability of evolutionary analog circuits: Band-pass filter case study,” HCI 2011 (accepted).

• H.-S. Park, and K.-J. Kim, “Systematic evaluation of island based real-valued genetic algorithm with graphics processing unit,” Korea Congress on Computer, vol. 37, no. 1(C), pp. 328-333, 2010.