kache@yacineMTB·Reply
by the way, the model has a discrete action space of 5. meaning it can only choose 5 forces on the cartpole (it isn't continuous action space) going to change that to make this a little easier
by the way, the model has a discrete action space of 5. meaning it can only choose 5 forces on the cartpole (it isn't continuous action space) going to change that to make this a little easier