This repository is a fork of a repository originally created by Lucas Descause. It is the codebase used for my Master's dissertation "Reinforcement Learning with Function Approximation in Continuing Tasks: Discounted Return or Average Reward?" which was also an extension of Luca's work.
python reinforcement-learning visualisation pytorch sarsa data-analysis convolutional-neural-networks asynchronous-methods deep-q-learning empirical-research reinforcement-learning-environments double-q-learning statistical-testing value-function-approximation return-formulations
- Updated
Sep 23, 2021 - Jupyter Notebook