lucidrains/q-transformer

Issues

• td loss: nan

  #18 opened 2 months ago by Michelangelo-Y
  2

• ValueError: could not broadcast input array from shape (8,) into shape (3,)

  #17 opened 2 months ago by Michelangelo-Y
  2

• how to get dataset?

  #6 opened a year ago by etoilestar
  1

• RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same or input should be a MKLDNN tensor and weight is a dense tensor

  #16 opened 2 months ago by Michelangelo-Y
  3

• Some personal questions

  #15 opened 5 months ago by heyi2025
  2

• question about Q-head

  #11 opened a year ago by 2M-kotb
  27

• Question about num_timestep

  #12 opened 10 months ago by carolineys
  10

• provide a complete example

  #13 opened 8 months ago by Johnly1986
  0

• Running the latest main branch with given usage example

  #10 opened a year ago by ramkumarkoppu
  1

• memmap can only handle max 2GB on certain systems

  #9 opened a year ago by ramkumarkoppu
  15

• A simple question about the code

  #8 opened a year ago by KID0031
  2

• integrate into stable-baselines3

  #5 opened a year ago by wenjun90
  3

• This is the final all code, will it be updated again?

  #3 opened a year ago by ltlhuuu
  4

• The rest part of the code?

  #2 opened a year ago by wukui-muc
  1