There are 1 repository under boltzmann-exploration topic.
See a program learn the best actions in a grid-world to get to the target cell, and even run through the grid in real-time! This is a Q-Learning implementation for 2-D grid world using both epsilon-greedy and Boltzmann exploration policies.
This github contains a simple OpenAi Gym Maze Enviroment and (at now) a RL Algorithm to solve it.
Using deep expected sarsa with tensorflow to solve the lunar lander problem with hyperparameter tuning and results analysis
This is a project of reinforcement learning which contains two different environments. The first environment is the taxi driver problem in 4x4 space with the simple Q-learning update rule. In this task, we compared the performance of the e-greedy policy and Boltzmann policy. As a second environment, we chose the LunarLander from the open gym. For the implementation of the project, the Policy gradient has been selected.