This repository contains information relating to experiments on algorithm performance in the OpenAI gym LunarLander-v2 environment. The experiments test and record the performance of various differentiations for deep reinforcement learning algorithms.
The Solved folder includes my writeup and information regarding an algorithm solving OpenAI's LunarLander-v2 enviornment. The Figure section contains graphs of performance metrics for algorithms with variations in performance and structure. A complete guide for how to install the LunarLander and LunarLanderContinuous enviornments can be found at the following link, https://medium.com/@brian.s.haney44/installing-spinningup-for-mac-os-x-9d5e24dc565a. A more general guide on reinforcement learning can be found here: https://medium.com/@brian.s.haney44/reinforcement-learning-5d578a0de1ff. A video of the optimized algorithm can be found at the following link, https://www.youtube.com/watch?v=5_f66jrAWiM.
Some scholarly articles on Deep Reinforcement Learning technology: