mimoralea / gdrl

Grokking Deep Reinforcement Learning
https://www.manning.com/books/grokking-deep-reinforcement-learning
BSD 3-Clause "New" or "Revised" License
798 stars 231 forks source link

Ch04 - strategies #15

Closed eyast closed 2 years ago

eyast commented 2 years ago

This book is awesome. I'm just leaving a note to anyone who wants to play with the code of Chapter 4 and test the simple strategies progressively with theEnvironemnt ("BanditSlipperyWalk-v0"). Within each loop, you need to reset the environment each time if you plan on inspecting the values of Q and Qe