-
Notifications
You must be signed in to change notification settings - Fork 3
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Video Rendering #6
Comments
Hi, |
Thank you for your prompt reply! I'm trying LLM-based agent, please keep this question open for further consultation. |
Hi! I tried to experiment with LLM-v2 agent driven by gpt-3.5-turbo API and render the representation video, so I modified starter_code.py as follows:
However, the program terminates after running to Environment Reset. The console output is as follows:
I checked the code and found that in src/HAZARD/challenge.py Line 280-283:
The return keyword may lead to the termination. Therefore, I want to know what the codes in src/HAZARD/challenge.py Line 280-283 do? How can I get the correct actions and video? Looking forward to your reply! |
Adding "demo" to the output directory will disable all agent actions and is used to demonstrate environmental changes. If you want to record agents, you can either not add "demo" or manually delete the lines of codes. |
Thanks for your excellent work! I'm new to embodied AI field. Currently I run the starter_code.py successfully, but I wanna render the result to a representation video, just like the More Agent Examples in the project page [https://vis-www.cs.umass.edu/hazard/]. How can I do this?
Looking forward to your reply!
The text was updated successfully, but these errors were encountered: