Open Source
I actively develop and maintain several open-source projects. While most are still in their early stages, I am continually improving them with the goal of contributing meaningful tools to the research community.
Reinforcement Learning
- mdptools: A Python library for solveing Markov Decision Processes (MDPs) using various algorithms, including value iteration, policy iteration, and Q-learning.
Paper with Code
- Liu, Ziang, and Tatsushi Nishi. “Inventory control with lateral transshipment using proximal policy optimization.” 2023 5th International Conference on Data-driven Optimization of Complex Systems (DOCS). IEEE, 2023. Code