RL course 2 Week 1 Blog

[sezan92]

Objective

This issue is about writup on week 1 RL course 2 blog

[sezan92]

Update 2024/07/30

• started from Week 2. Definition of Monte Carlo method done.

ToDO

• https://www.coursera.org/learn/sample-based-learning-methods/lecture/7F85i/using-monte-carlo-for-prediction

[sezan92]

Update 2024/08/09

• Course 2 Week 2 #42 started

TODO

• complete it.

[sezan92]

Update 2024/08/22

• video 2 done. could not get it well. check the book

TODO

• check the book on monte carlo black jack

[sezan92]

Update 2024/08/28

• wrote intuition

TODO

• Start video 3

[sezan92]

Update 2024/09/02

• started video 3 and 4. that means monte carlo action value update and general policy iteration

TODO

• update the intuition on penalty (slight wrong)
• write up inteution
• [ ]

[sezan92]

2024/09/11

• updated the penalty example.
• started video on exploring starts, name "solving blackjack example".

TODO

• complete and intuition on exploring starts, and epsilon soft policy in one go