Highlighted by Chuanlin Zhao

- From Simple Reinforcement Learning with Tensorflow Part 0: Q-Learning with Tables and Neural Networks by Arthur Juliani
In it’s simplest implementation, Q-Learning is a table of values for every state (row) and action (column) possible in the environment. Within each cell of the table, we learn a value for how good it is to …

- From Simple Reinforcement Learning with Tensorflow Part 0: Q-Learning with Tables and Neural Networks by Arthur Juliani
… time is impossible, but learning to avoid the holes and reach the goal are certainly still doable. The reward at every step is 0, except for entering the goal, which provides a reward of 1. Thus, we will need an algorithm that learns long-term expected rewards. This is exactly what Q-Lear…

- From Simple Reinforcement Learning with Tensorflow Part 0: Q-Learning with Tables and Neural Networks by Arthur Juliani
…he goal block, a safe frozen block, or a dangerous hole. The objective is to have an agent learn to navigate from the start to the goal without moving onto a hole. At any given time the agent can choose to move either up, down, left, or right. The catch is that …