Deep Reinforcement Learning in Unity: With Unity ML Toolkit

© Abhilash Majumder 2021

A. MajumderDeep Reinforcement Learning in Unityhttps://doi.org/10.1007/978-1-4842-6503-1_7

7. Case Studies in ML Agents

Abhilash Majumder¹  

(1)

Pune, Maharashtra, India

 

At this stage, we have gained considerable knowledge as to the flexibility of the ML Agents Toolkit. We have also learned different complex algorithms that are related to deep RL. If we analyze, we can visualize that the main idea of any RL algorithm is to provide a set of decisions that the agent can follow to achieve a particular goal. Although we covered most of the deep learning algorithms, there is a set of algorithms that do not follow the traditional approach of backpropagation and gradient ascent/descent. In this chapter, we will explore evolutionary ...