Q learning
singlasahil14 opened this issue · comments
How does explore = 0 imply that the agent is not getting trained? Ideally the _learn function will still be called and the agent will learn. Is it an error or some flaw in my understanding?
yes, the agent does get trained there. that could be clarified as "before training" instead of "without training" - I'll update it in a sec
let me know if that's clearer!
Yes its clearer. Thank you