ski is a package for educational purposes
Project description
ski
ski is a Python package for running reinforcement learning (RL) experiments on an inventory control problem called retailing skis (Eric V. Denardo [1982]). The problem is formulated as Markov decision process (MDP) and solved by fundamental RL algorithms including Monte Carlo (MC) method, Sarsa, Q-learning, and double Q-learning in both tabular and value approximation manner.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ski-0.1.12.tar.gz
(7.0 kB
view hashes)
Built Distribution
ski-0.1.12-py3-none-any.whl
(8.2 kB
view hashes)