Norio Kosaka(小坂 紀夫)
email:
kosakaboat[at]gmail.com
CV |
Scholar |
Github |
LinkedIn
|
I finished MSc Machine Learning with Distinction at Royal Holloway University of London and worked on the intersection of Reinforcement Learning & Robotics for my Master Thesis. I am proud to be advised by Prof. Chris Watkins with the thesis.
My research interests: Model-based Planning(e.g., MPC) in RL, Offline Policy Evaluation(aka Counterfactual Evaluation), Listwise Recommender Systems.
My team at NAVER hosts a weekly study group in which we discuss a variety of ML topics, so please let me know if you are interested. Any topic is welcome so that let's discuss together!!
|
|
Know Your Action Set: Learning Action Relations for Reinforcement Learning
Ayush Jain*, Norio Kosaka*, Kyung-Min Kim, Joseph J Lim
International Conference on Learning Representations 2022, Apr. 2022
|
|
PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference
Masashi Okada, Norio Kosaka, Tadahiro Taniguchi
International Conference on Intelligent Robots and Systems(IROS) 2020, USA, Oct. 2020
|
|
Has it explored enough
Norio Kosaka
Master's Thesis at Royal Holloway, University of London, Sep. 2019
|
|