Research Interests

Artificial Intelligence, Reinforcement Learning, Human-Agent Interaction, Heuristic Search, Constrained/Multi- Objective Optimization, Decision Theory

Education

  • Ph.D., College of Information and Computer Sciences, University of Massachusetts Amherst
  • M.S., Department of General Systems Studies, Graduate School of Arts and Sciences, University of Tokyo
  • B.A. in Informatics, Department of Interdisciplinary Sciences, College of Arts and Sciences, University of Tokyo

Publications

Letters

  • Kazumi Kasaura*, Shuwa Miura*, Tadashi Kozuno, Ryo Yonetani, Kenta Hoshino, and Yohei Hosoe. 2023. Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints. IEEE Robotics and Automation Letters (RA-L). *These authors contributed equally to the work. paper code

Conference Papers

  • Shuwa Miura, Olivier Buffet, and Shlomo Zilberstein. 2024. Approximation Algorithms for Observer Aware MDPs. In Proceedings of the 40th Conference on Uncertainty in Artificial Intelligence (UAI). paper code
  • Shuwa Miura and Shlomo Zilberstein. 2024. Observer-Aware Planning with Implicit and Explicit Communication. In Proceedings of the 23rd International Conference on Autonomous Agents and MultiAgent Systems (AAMAS). paper
  • Shuwa Miura, Kyle Hollins Wray, and Shlomo Zilberstein. 2022. Heuristic Search for SSPs with Lexicographic Preferences over Multiple Costs. In Proceedings of the Fifteenth Annual Symposium on Combinatorial Search (SOCS). Honorable Mention Student Paper. paper
  • Shuwa Miura and Shlomo Zilberstein. 2021. A unifying framework for observer-aware planning and its complexity. In Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence (UAI). paper
  • Shuwa Miura, Andrew. L. Cohen, and Shlomo Zilberstein. 2021. Maximizing Legibility in Stochastic Environments. In Proceedings of 2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN). paper
  • Shuwa Miura and Alex Fukunaga. 2017. Automatic Extraction of Axioms for Planning. Proceedings of the Twenty-Seventh International Conference on Automated Planning and Scheduling (ICAPS). Honorable Mention for Best Student Paper. paper

Extended Abstracts

  • Shuwa Miura and Shlomo Zilberstein. Maximizing Plan Legibility in Stochastic Environments(Extended Abstract). 2020. In Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems.
  • Shuwa Miura and Alex Fukunaga. Automatically Extracting Axioms in Classical Planning (Extended Abstract). In Proceedings of Thirty-first AAAI Conference on Artificial Intelligence, San Francisco, 2017.

Workshop Papers

  • Shuwa Miura. 2022. On the Expressivity of Multidimensional Markov Reward. RLDM2022 Workshop on RL as a Model of Agency. paper
  • Shuwa Miura and Alex Fukunaga. 2017. Axioms in Model-based Planners. ICAPS17 Workshop on Planning, Search, and Optimization (PlansOpt).