search

Atcold / pytorch-PPUU

Code for Prediction and Planning Under Uncertainty (PPUU)
https://youtu.be/X2s7gy3wIYw
MIT License
203 stars 54 forks source link

Issue in dumping "state, action, cost" triple #67

Closed jayabrata97 closed 2 years ago

jayabrata97 commented 2 years ago

I was trying run generate_trajectories.py. However, it was giving error TypeError: step() missing 1 required positional argument: 'action' on line 90 observation, reward, done, info = env.step(). I changed it to observation, reward, done, info = env.step(np.zeros((2,))). Then it started building pkl files. @Atcold , is it correct?

lucywang720 commented 2 years ago

I have the same problem, do you solve it?

jayabrata97 commented 2 years ago

Yes.

lucywang720 commented 2 years ago

So observation, reward, done, info = env.step(np.zeros((2,))) is correct or not?

jayabrata97 commented 2 years ago

So observation, reward, done, info = env.step(np.zeros((2,))) is correct or not?

Correct, it worked for me.

lucywang720 commented 2 years ago

So observation, reward, done, info = env.step(np.zeros((2,))) is correct or not?

Correct, it worked for me.

Thank you a lot!!

Atcold commented 2 years ago

Can you send a patch to fix this issue?

jayabrata97 commented 2 years ago

Hi @Atcold, https://github.com/Atcold/pytorch-PPUU/blob/2e087d9ef556cf75723ff2c5f5b71c4bb0b358dc/generate_trajectories.py#L90

I changed this line. By the way, thanks for the deep learning course lectures. I came to know about the paper from there.

Atcold commented 2 years ago

I meant asking whether you'd like to send a PR and/or edit the file directly. So you'll be a contributor ;) and automatically close this issue.

jayabrata97 commented 2 years ago

Hi @Atcold, sorry for the late reply. I would like to edit the file directly. Thank you very much for considering me as a contributor. I will open a PR.

Atcold commented 2 years ago

Just click on the ✏️ and edit the file. Don't forget to type "close #67" in your commit message to automatically close this issue.