Hi!
I’m wondering whether this competition challenges us with a multi-task setting.
To my understanding, one agent shall train on 16 environments So this agent/model should be able to play each environment and the 4 unseen ones, right?
@Leckofunny: while there are multiple environments that your submitted code will be evaluated against, there is no expectation to jointly learn across all the environments.
Your code will be evaluated independently across each of the N environments (depending on the round), and then the performances across all aggregated.
So in practice, if your submission is being evaluated against N different environments, then at the end of the N parallal training phases, we will have N different agents, one for each of the environments.
Hope this is clarifying,
Cheers,
Mohanty
According to this image, each environment is being trained and evaluated solely.
After all, the agent gets to train on the unknown environments as well, right?
And does this image mean that the training and the evaluation are done on your side?
Hello @Leckofunny
Yes, the agent will be trained on unknown environments as well. The training and rollouts are done on the server-side. You only need to submit the code. You will be given access to the training logs once you make a submission.