Deadline Extended to Feb 8 + Instructions for Final Submission Package

our project is here. if you can’t see ours due to the issue. let me know.

View post 0

Deadline Extended to Feb 8 + Instructions for Final Submission Package

@aicrowd_team I cannot find the @aicrowd name in GitLab’s “Invite a group” window.

View post 0

Possible Mario simulation bug?

Please check this thread @howon_lee

View post 1

Obs_str position misalignment: Mario's coordinates gradually drift from the actual position

Thank you for your reply!
I hope they can fix this problem ASAP. @howon_lee

View post 0

Obs_str position misalignment: Mario's coordinates gradually drift from the actual position

Hi,

I’m facing a bug where the obs_str representation of the screen gradually loses sync with Mario’s actual position.

It works fine at the very beginning (Spawn point), but the more I move, the more it drifts. It gets especially bad when I jump near obstacles like pipes. It feels like the text observation isn’t keeping up with the screen scrolling properly.

Does anyone know why this gradual misalignment happens?

View post 0

📹 Q&A with Challenge Organisers | Join the Townhall 9th January 11:00 AM KST

Hello,

I am currently participating in Track 1 of the Orak Challenge.

I have a few specific inquiries regarding the constraints on agent implementation. Could you please clarify the following points?

1. Internal Operations: Are we permitted to perform tasks such as pre-processing data, post-processing outputs, or enabling tool usage? Do we have full freedom to implement the agent’s internal logic beyond these examples?
2. LLM Call Frequency: Is there a strict rule that one act call must correspond to exactly one LLM call? Is it permissible to make multiple LLM calls or no calls at all within a single act step?
3. Model Usage: Is it mandatory to use a single 8B LLM to play all 4 games?
4. Timeout Settings: Is it allowed to adjust the timeout limit to accommodate computing power limitations?

I want to make sure there are no limitations on the internal logic or processes.

Thank you.

View post 1

Intermittent UNAUTHENTICATED: Session expired (timeout: 120s) across all games (local + remote)

Can I change timeout time due to computing power?

View post 1

Inquiry regarding Agent Implementation for Track 1

Hello,

I am currently participating in Track 1 of the Orak Challenge.

I would like to ask if there are any specific constraints regarding the agent implementation. Aside from the requirement to use an LLM with 8B parameters or fewer, are there any restrictions on the internal operations of the agent?

Specifically, I would like to confirm if we are permitted to perform tasks such as pre-processing data, post-processing outputs, or enabling tool usage. Furthermore, could you please confirm if we have full freedom to implement the agent in any other way beyond the examples listed above?

Additionally, I would like to ask if there is a strict rule that one act call must correspond to exactly one LLM call, or if it is permissible to make multiple calls or no calls at all within a single act.

And Do I have to play 4 games with just one 8B llm?

I want to make sure there are no limitations on the internal logic or processes.

Thank you.

View post 0