/dqn_chsel

Primary LanguagePython

dqn_chsel

Current

  1. Diff of F1 score as reward (using test dataset)
  2. Base channel C3 and C4
  3. Log with average of F1 score
  4. simple DQN
  5. episode terminated if either diff f1 < 0, steps 6 times or choose 9 chs

Todo

  • ActorCritic
  • Another classifier

Examine

  • Another reward type
  • Another rules
  • train data = fit model
  • validation = update weigth
  • test = test