LyWangPX / Reinforcement-Learning-2nd-Edition-by-Sutton-Exercise-Solutions

Solutions of Reinforcement Learning, An Introduction

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Exercise 3.4 - 0 probability rows

gblawrence03 opened this issue · comments

The question states that the table should have "a row for every 4 tuple for which p(s', r | s, a) > 0". Therefore the rows where p(s', r | s, a) = 0 should be omitted.