Publication

A. Peer-reviewed Journal Articles

A1. M. Ohnishi, and M. Yukawa, “Online Nonlinear Estimation via Iterative L2-Space Projections: Reproducing Kernel of Subspace”, IEEE Transactions on Signal Processing (TSP), vol. 66, no. 15, pp. 4050-4064, 2018. available at Xplore or at arXiv(Accepted version)

A2. M. Ohnishi, L. Wang, G. Notomista, and M. Egerstedt, “Barrier-Certified Adaptive Reinforcement Learning with Applications to Brushbot Navigation”, IEEE Transactions on Robotics (TRO), under review (conditionally accepted). available at arXiv

B. Peer-reviewed Conference Papers

B1. M. Ohnishi, and M. Yukawa, “Online learning in L 2 space with multiple Gaussian kernels”, European Signal Processing Conference (EUSIPCO), pp. 1594-1598, 2017. available at Xplore

B2. M. Ohnishi, M. Yukawa, M. Johansson, and M. Sugiyama, “Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces”, Advances in Neural Information Processing Systems (NeurIPS) 31, 2018. (presented at NeurIPS2018, Montreal, Quebec, Canada, Dec. 5, 2018). available at arXiv. Poster is available at Poster.

C. Thesis

C1. “Safety-aware Adaptive Reinforcement Learning with Applications to Brushbot Navigation”, KTH, School of Electrical Engineering and Computer Science (EECS), Automatic Control, 2018, (Supervised by M. Egerstedt, Examined by M. Johansson). available at KTH DiVA