Grokking Deep Reinforcement Learning Chapter 4 examples - balancing exploration and exploitation

This video shows a comparison of different exploration and exploitation options for training a reinforcement learning agent. Top options like Upper Confidence Bound, Epsilon greedy, and Thompson combine exploration and exploitation to find the Q that leads to the highest long-term reward in the environments.
References:
Book:
www.amazon.com...
Project:
github.com/mim...
Code:
github.com/mim...