A Crash Course on Reinforcement Learning
It serves as an educational resource for beginners in reinforcement learning, offering a foundational understanding without presenting new research.
This paper provides an introductory overview of reinforcement learning, covering its applications in domains like strategy games and robotics, and discusses three approaches—Policy Gradient, Policy Iteration, and Model-building—for solving RL problems in both discrete and continuous action spaces.
The emerging field of Reinforcement Learning (RL) has led to impressive results in varied domains like strategy games, robotics, etc. This handout aims to give a simple introduction to RL from control perspective and discuss three possible approaches to solve an RL problem: Policy Gradient, Policy Iteration, and Model-building. Dynamical systems might have discrete action-space like cartpole where two possible actions are +1 and -1 or continuous action space like linear Gaussian systems. Our discussion covers both cases.