jtwwang/hanabi

Issues

• Legal action detection in probabilistic settings

  #50 opened 5 years ago by LorenzoM1997
  0

• Third-person action in probabilistic settings

  #49 opened 5 years ago by LorenzoM1997
  0

• Testing new transition function

  #48 opened 5 years ago by LorenzoM1997
  0

• State transition "play" move

  #19 opened 5 years ago by LorenzoM1997
  0

• Implement discard move

  #17 opened 5 years ago by LorenzoM1997
  0

• Implement move "reveal color"

  #18 opened 5 years ago by LorenzoM1997
  0

• Have experience.load load episodes randomly.

  #47 opened 5 years ago by jtwwang
  1

• Try different strides and filter_sizes

  #46 opened 5 years ago by jtwwang
  0

• Try DeepMind's NALU for numerical inputs

  #45 opened 5 years ago by jtwwang
  0

• Benchmark performance on RainbowAgent

  #44 opened 5 years ago by jtwwang
  0

• Seperate observation into heads

  #43 opened 5 years ago by jtwwang
  0

• Need to fill observation stack and history of game correctly

  #27 opened 5 years ago by LorenzoM1997
  1

• Error in the MC Agent

  #30 opened 5 years ago by LorenzoM1997
  0

• Makefile:83: recipe for target 'all' failed

  #8 opened 5 years ago by harshita-kaushal
  1

• crash when running rainbow agents for multiple episodes

  #5 opened 6 years ago by LorenzoM1997
  2

• Error when trying to retrieve the card_knowledge()[][].color_plausible()

  #1 opened 6 years ago by LorenzoM1997
  0