Thank you for your continued participation in the Learn to Race Challenge.
As the Top 10 teams from Round 1 move to Round 2, we wanted to share an update on the challenge timeline and prize details.
- We are readying the setup for Round 2, where your agents will be evaluated on an unseen track, and expect to have it ready before the end of this week.
- The end date of the second round will also be updated based on the launch date.
- The teams/participants that move to Round 2 will also receive training credits. We expect to deliver these by tomorrow.
Hey, I wanted to follow up on this. Have not seen an announcement yet as to what the dates are going to be, and what the submission parameters will be like (how many submissions, @ what frequency?). I have also not yet received the training credits yet, will we get those before stage 2 also?
Thanks for your continued patience on the launch of Stage 2!
We are working to incorporate participant feedback/concerns, before the Stage 2 launch, to ensure that Stage 2 remains both fair and accommodating. We are again expecting a launch this week, as we are in the final stages of testing various model types and configurations.
There will be no restriction on the submission frequency, subject to the server’s ability to perform the ‘practice’ phases and main evaluations, in a timely manner. We will adopt the same protocol as before, for allowing teams to request AWS credits: 🏗️ Claim Your Training Credits
A brief word about Stage 2: this phase of the competition really tests agents’ abilities to safely generalise to unseen environments. We encourage participants to optimise their approaches, specifically for this safe generalisation capability, by experimenting offline with the Anglesey track as a target environment. Transfer learning techniques such as domain adaptation, *-shot learning, knowledge distillation, or self-supervision/self-training — e.g., making use the sensory information that is available during the ‘practice phase’ but will not be available during the main evaluation — may prove useful; leveraging domain knowledge about the road features may be crucial. Indeed, participants will submit their models for a 1-hour practice period, wherein agents will be free to perform optimizer updates. Afterwards, the resultant checkpoint from the practice phase will be tested on the simulated North Road track at Las Vegas Motor Speedway.
Very much looking forward to it!
so stage2 is not launched yet, am I right?
I see someone have already submit to the leaderboard, but when I submit, nothing happen.
I mean when I submit with a new tag, no issue tracker shows up like in stage 1. is this normal?
I think that maybe we were not meant to be able to submit before, but could. So they have blocked submissions now, if your submission says
Submission failed : Failed to communicate with the grader. then it isn’t on your side.