Note 1: the previous character positions are the position in the previous frame, and if the game runs at 60 fps the previous position is not that different from the current one. glad if you could explain what's causing the bot to be so bad or what's not helping him to learn properly.Īlthough I think that the fitness function and the inputs should be the only problem I'm attaching the python-NEAT config file. ![]() I'm not so proficient with neuroevolution and I'm probably doing something wrong. (list of the 3-7 next platforms locations).These are the inputs I tried to mess around with: ![]() I tried several input configurations to make the bot perform better. When I look at the characters jumping it looks like they just always jump and go left or right and not deliberately aiming to the next platform. 200 means 20 platforms which is not a lot). The problem I'm facing is that the bot isn't learning good enough after 1000 generations the best score was around 200 (it can get to 200 even at the first few generations by mistake. right now the fitness is the number of platforms they jumped on, each platform gives +10. ![]() I rebuilt the game using pygame and I'm trying to build the bot using Python-NEAT.Įvery generation a population of 70 characters tries to jump to the next platform and increase their fitness. I'm trying to make a bot to the famous " Icy Tower" game.
0 Comments
Leave a Reply. |