6 events
when toggle format what by license comment
Jun 17 '20 at 9:57 history edited CommunityBot
Commonmark migration
Apr 24 '18 at 21:59 comment added BlueMoon93 Yeah, usig raw image pixels as you were probably using works with convolutional layers, but not so well with QTables (too large of a state space). However, you can preprocess the image and obtain simpler states. I.e, extract features from the image and feed a simpler local-perspective grid to QLearning
Apr 20 '18 at 19:25 comment added Tech I mean that in the game players spawn in random places and as they move, they leave a permanent trail behind them that kills other players if they touch it. My thinking was that Q-tables wouldn't work well with this. Also yes, my input is downized frames in real time. TimeDistributed Conv2D in Keras using 4 frames in 3 channels (different player colors), if that says anything to you.
Apr 20 '18 at 16:12 comment added BlueMoon93 What do you mean, the environment constantly changes? Are you processing image input? Do you mean there is an excessively large state space? You can either pre process the images, or extract features first and use those as input. This is a very common ML step, improving your algorithms input.
Apr 20 '18 at 13:16 comment added Tech Thanks for your answer! I didn't use the original Q learning since the environment constantly changes, and I don't see how a Q-table can work with that, but I'll try your suggestions!
Apr 19 '18 at 18:02 history answered BlueMoon93 CC BY-SA 3.0