Location
Badges
Activity
Ratings Progression
Challenge Categories
Challenges Entered
ASCII-rendered single-player dungeon crawl game
Latest submissions
Training sample-efficient agents in Minecraft
Latest submissions
Measure sample efficiency and generalization in reinforcement learning using procedurally generated environments
Latest submissions
See Allgraded | 77427 | ||
graded | 77411 | ||
graded | 77317 |
Multi-Agent Reinforcement Learning on Trains
Latest submissions
Sample-efficient reinforcement learning in Minecraft
Latest submissions
Disentanglement: from simulation to real-world
Latest submissions
See Allgraded | 21041 | ||
graded | 21039 | ||
graded | 21038 |
Sample-efficient reinforcement learning in Minecraft
Latest submissions
Latest submissions
A new benchmark for Artificial Intelligence (AI) research in Reinforcement Learning
Latest submissions
Multi-Agent Reinforcement Learning on Trains
Latest submissions
Participant | Rating |
---|
Participant | Rating |
---|
NeurIPS 2019 : Disentanglement Challenge
What changes should one make to let evaluation work?
Over 4 years agoI built the image following the instructions and ran into no problem. The execution was able to submit.
What changes should one make to let evaluation work?
Over 4 years agoYes, I installed the dependencies from the requirement.txt
file in the starter kit. The environment.yml
exported is here https://gitlab.aicrowd.com/siyuzhou/neurips2019-disentanglement-challenge/blob/master/environment.yml. tensorflow-gpu==1.13.1
and is the one from pip
not conda
.
What changes should one make to let evaluation work?
Over 4 years agoThank you. I am using the starter kit which has the aicrowd_helpers.submit()
included in the end of train_tensorflow.py
. I added local_evaluation.py
as a hack, in the hope that it would fix inconsistency in environment variables which I suspected was the cause.
The error message you pasted makes very little sense to meβ¦ But Iβll try look into it.
What changes should one make to let evaluation work?
Over 4 years agoThank you for your response. Iβve had many failed submissions. https://gitlab.aicrowd.com/siyuzhou/neurips2019-disentanglement-challenge/issues/5 is the one I was referring to. I use TensorFlow. I got a successful submission later https://gitlab.aicrowd.com/siyuzhou/neurips2019-disentanglement-challenge/issues/8. The only change I made was to invoke local_evaluation.py
in run.sh
. Whatβs causing the failure?
What changes should one make to let evaluation work?
Over 4 years agoHi, I used the latest repo for submissions but always got failed evaluation. I notice that despite me not using pytorch for training, I have to include pytorch as a dependency to make it past the image building stage. aicrowd_helper.submit()
is indeed included in the original tensorflow code, but the evaluation fails regardless in my case. What else should I do to have a successful submission? Iβm sorry if this appears to be a dumb questionβ¦
Model error many times
Over 4 years agoI have got the same error. I didnβt use Pytorch in the training, so would it still require PyTorch as a dependency? Anyway I included PyTorch in my latest submission. However, the submission has been in queue for over a day. Iβm not sure how common the issue is, but I do notice almost all recent submissions turn out to be failure.
What changes should one make to let evaluation work?
Over 4 years agoAll my recent submissions get this error after the successful one: βUnable to listen to messages intended for the Oracle. Please contact administratorsβ. I wasnβt even able to reproduce the successful submission with the same settings. For example, https://gitlab.aicrowd.com/siyuzhou/neurips2019-disentanglement-challenge/issues/12, along with 3 other submissions in a row. I disabled local evaluation in the latest failed submission. Whatβs going onβ¦