🌐 Edge#99: What are Trust Region and Proximal Policy Optimization; PPO to master Dota2; and RLlib

RL-series goes on

In this issue:

• we discuss what are trust region and proximal policy optimization; 

• we explore RLlib – an open-source framework for highly scalable reinforcement learning;

• we learn how OpenAI used PPO reinforcement learning to master Dota 2.  

💡 ML Concept of the Day: What are Trust Region and Proximal Policy Optimization?

In Edge#97, we continue our series…