- Megumi Miyashita, Shiro Yano and Toshiyuki Kondo, Evaluation of Safe Reinforcement Learning with CoMirror Algorithm in a Non-Markovian Reward Problem, 17th International Conference on Intelligent Autonomous Systems (IAS-17), Zagreb, Croatia, (6/13-16, 2022).
- Megumi Miyashita, Toshiyuki Kondo, Shiro Yano, Reinforcement Learning with Constraint based on Mirror Descent Algorithm, Results in Control and Optimization, doi: 10.1016/j.rico.2021.100048, 2021.
- Megumi Miyashita, Shiro Yano, Toshiyuki Kondo, Mirror Descent Search and its Acceleration, Robotics and Autonomous Systems, Vol.106, pp.107-116, 2018. DOI: 10.1016/j.robot.2018.04.009. Journal site
- Megumi Miyashita, Ryo Hirotani, Shiro Yano, and Toshiyuki Kondo, Direct Policy Search with Extremum Seeking, SICE Annual Conference 2017, Kanazawa University, Japan. (9/22, 2017)
- Megumi Miyashita, Ryo Hirotani, Shiro Yano, and Toshiyuki Kondo, Experiment of Reinforcement Learning with Extremum Seeking, The 2017 6th ICT International Student Project Conference (ICT-ISPC2017), hosted by the Faculty of Computing, Universiti Teknologi Malaysia (UTM), Malaysia (5/23, 2017)