Reinforcement Learning — Generalisation in Continuous State Space

Function Approximation with Random Walk Example

Till now I have introduced most basic ideas and algorithms of reinforcement learning with discrete state, action settings. Recall the examples we have been implemented so far, Grid World, Tic-Tac-Toe, Multi-Arm Bandits, Cliff Walking, Blackjack … etc, most of which has a basic setting of a board or a grid in order to make the state space countable. However, the power of reinforcement learning does not stop there, and in a real world…