PKU-Alignment/Safe-Policy-Optimization

Issues

• Doubt about the updating method of Lagrange Multipliers

  #69 opened a year ago by lijie9527
  6

• Question about the torch.size of loss_pi in focops implement

  #68 opened a year ago by lijie9527
  2

• Question about logger value

  #66 opened a year ago by lijie9527
  2

• question about env reset

  #65 opened a year ago by lijie9527
  2

• Something about IPO

  #23 opened 2 years ago by stvsd1314
  3

• Question about rescale in cpo

  #22 opened 2 years ago by YUYING07
  1

• Safexp-PointGoal1-v0 vs SafetyPointGoal1-v0

  #21 opened 2 years ago by YUYING07
  2

• Question about the implementation of the IPO

  #18 opened 2 years ago by aygonl
  1

• why?

  #19 opened 2 years ago by Yifei-Bi
  3

• Process conflict casused abnormal termination

  #1 opened 3 years ago by guanjiayi
  4