justinjfu/inverse_rl

Issues

• Discrepancy between the Ant experiment in the paper and the code.

  #11 opened 3 years ago by HesNobi
  0

• NotImplementedError

  #8 opened 6 years ago by lujiayou123
  3

• Number of iterations of policy optimization

  #9 opened 4 years ago by Jendker
  0

• Doubt on the re-optimization of reward

  #10 opened 5 years ago by SestoAle
  0

• PyTorch Implementations

  #7 opened 6 years ago by rchavezj
  0

• Rolling out IRL policy

  #6 opened 6 years ago by glebshevchukk
  0

• Running Swimmer, HalfCheeta, Humanoid etc

  #5 opened 6 years ago by ahq1993
  1

• No support for discrete action spaces in batch policy optimization

  #4 opened 6 years ago by Maathuis
  0

• Assert in AIRL

  #3 opened 6 years ago by Maathuis
  0

• Full Code Release

  #2 opened 7 years ago by Feryal
  2

• Examples with GCLDiscrimTrajectory

  #1 opened 7 years ago by dcnhan
  0