marload/DeepRL-TensorFlow2

Issues

• "PPO_Continuous.py" trained 1000 EP without effect

  #3 opened a year ago by Synmul
  4

• Reward modification in PPO

  #7 opened 4 years ago by Ynjxsjmh
  2

• .

  #10 opened 2 years ago by ZeroNilZero
  0

• A3C_continues.py

  #9 opened 3 years ago by Gjunze
  0

• Probelm in A3C continuous

  #8 opened 3 years ago by Miftahur92
  0

• Any idea why DQN is slow on CPU and on GPU?

  #6 opened 4 years ago
  0

• From_logit in A2C_discrete.py should be False

  #5 opened 4 years ago by gzlong96
  0

• Hyper-parameters for successful DQN Agent

  #1 opened 5 years ago by ichko
  5