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_6

6. Competitive Networks for AI Agents

Abhilash Majumder¹  

(1)

Pune, Maharashtra, India

 

In the last chapter, we studied the different parts of deep reinforcement learning (RL) and also studied the interactivity of the Python API to build custom models. Since there are various paradigms inside RL, we will be exploring adversarial and cooperative learning in addition to curriculum learning. Since we have an idea of the actor critic class of algorithms, including proximal policy operation (PPO), we will also look into an off-policy counterpart that we mentioned in the last chapter: deep deterministic policy gradient (DDPG). The important ...