search

karl-hajjar / RL-solitaire

Solving the game of peg solitaire with a Reinforcement Learning Algorithm.
3 stars 2 forks source link

Replicating the results #2

Open MFormenti opened 4 months ago

MFormenti commented 4 months ago

Hi! I've been trying to replicate the results you mentioned using the configuration provided, but I've been having some issues. I tried to run the training as mentioned in the readme a couple of times, but I can't even come close to the results you mention. I then tried to edit the config file, but I couldn't really understand how it works or how all the parameters are used. I was especially confused by the seed in the config file, which seems to be left void, but every time I run the training, the seed is set to 42. Could you please help me better understand how the training works and how I can properly edit the config file and the different parameters in the training?

annahambi commented 3 months ago

I have the same question as @MFormenti