search

SaminYeasar / Off_Policy_Adversarial_Inverse_Reinforcement_Learning

Implementation of Off Policy Adversarial Inverse Reinforcement Learning
MIT License
20 stars 2 forks source link

Hyperparameters for expert trajectories #2

Closed sff1019 closed 3 years ago

sff1019 commented 3 years ago

Thank you for your amazing work!

I am also trying to use off-policy in my IRL project, however, I am having a hard time creating expert trajectories. I found that you have achieved good expert trajectories in your work, and I was curious if it was possible for you to share the expert trajectories for your experiments. Especially, it would be great if you can include the data for PointMazeLeft.

SaminYeasar commented 3 years ago

Hi, the link for the expert trajectories is shared in the repository (link provided in the readme file). Please let me know if the link does not work

sff1019 commented 3 years ago

@SaminYeasar I saw the link, but these does not include the hyperparameters for the training. Will it be possible for you to share these as well?