search

rdgreene / sa_tsp

Q-Learning applied to the classic Travelling Salesman Problem
18 stars 3 forks source link

Set the parameter values for Q-learning #9

Open miguelesteras opened 7 years ago

rdgreene commented 7 years ago

Almost done, just need to add a brief description of the role of learning rate (alpha) and discount factor (gamma).

rdgreene commented 7 years ago

Ok, I'm pretty sure I'm done here. I think it's pretty thorough (maybe too thorough 🤓 , but there's no word limit so I'm not worried about this being a problem#0. You might want to give it a proof read, just to confirm you agree with my definition and formalisation of the parameters. Let me know when you do this, and if you give it the ok I'll close the issue 💪