Taipei City, TW
Ratings Progression
Challenge Categories
Challenges Entered
Completed
Unity Technologies
A new benchmark for Artificial Intelligence (AI) research in Reinforcement Learning
Latest submissions
See All| graded | 3236 | ||
| graded | 3107 | ||
| graded | 3104 |
Unity Obstacle Tower Challenge
Submissions Q&A
About 1 year agoYou should read all post in this discourse. So much people use dopamine.
If you have problem in submission, you should check again your code and read post again.
Now, all dopamine user are successfully submitted.
Read again~
Couldn't launch the obstacletower environment
About 1 year agoDopamine
|
_dopamine
Obstacletower
|
_obstacletower.x86_64
If terminal run here
You can find path in unity_lib
Couldn't launch the obstacletower environment
About 1 year agoDownload OTC env linux.zip file
The link
Submissions Q&A
About 1 year agoBefore your Submissions Question:
This is debugged with my 35 submission experience.
I am also a contestant, I am not an official staff member.
In order to compete fairly, I hope everyone can break through 100 floors.
Due to some inherent instability in Unity Env, it is a bit special.
Thanks for @mohanty help
This assumes that you are already able to run tests locally.
Check these step:
Update your env to least version.
Q:“mlagents_envs.exception.UnityTimeOutException: The Unity environment took too long to respond”
A:This is open issue.
2 steps
Change timeout > 300s
env = ObstacleTowerEnv(args.environment_filename, docker_training=args.docker_training, retro=True, timeout_wait=600)
It is recommended to perform the import of agent tensorflow after env.is_grading() before the official release of the new environment file.
if env.is_grading():
import tensorflow as tf
import youragent
while True:.......
Q: bash >>> ^M
A:
The newline symbol for the Dos file is ^J^M
The newline symbol for Unix files is ^J
So in some cases you will encounter bash problems, because it is the relationship of the Windows environment configuration file, you should use Vim and other similar editors to change the encoding.
Q: ckpt import error (ex gzip broken)
A:Follow this
[Announcement][git error] Large Model Weights in your Submission Repository
About 1 year ago@mohanty i have 200mb ckpt file also can’t upload too.
[Announcement][git error] Large Model Weights in your Submission Repository
About 1 year agoI have same problem, but you can try git lfs pull
[Announcement][git error] Large Model Weights in your Submission Repository
About 1 year ago2019-03-08T16:41:29.918810415Z INFO:mlagents_envs:Start training by pressing the Play button in the Unity Editor.
2019-03-08T17:31:30.971471728Z ckpt: 135 MB
Have something wrong?
https://gitlab.aicrowd.com/ChenKuanSun/obg/issues/4
Evalutation error : Unity environment took too long to respond
About 1 year agohttps://gitlab.aicrowd.com/ChenKuanSun/obg/issues/1
If the evaluation system is in the same environment, will it be because the worker_id is not set and the startup fails? When others are evaluation?
[Announcement][git error] Large Model Weights in your Submission Repository
About 1 year agoremote: fatal: pack exceeds maximum allowed size
error: pack-objects died of signal 13
@mohanty
Suggest for competition
About 1 year agoOK , I try again~~~~~~
Can that help me increase my quota, because this doesn’t seem to be because of the problem I submitted?
Suggest for competition
About 1 year agoI mean the participants want to simulate the configuration of the environment themselves, they can use these methods.
Can you please help me by the way to check why my CKPT file will have a wrong problem when clone to build from repo?
The correct size should be 4-5GB
Suggest for competition
About 1 year agoIt is currently known that the biggest difficulty for competitors is the submissions.
Although we have good validation on local, even GCP
But there are still many people who have encountered difficulties.
This is nothing about Reinforcement Learning, but I feel that only knowing that the solution is not a good competition.
Here are some of the results I tested in the past few days that I consumed my quota.
The image file currently used by Aicrowd:
nvidia/cuda:9.0-cudnn7-runtime-ubuntu16.04
So the way to test similar environments can be set in GCP Compute.:
My language is Chinese, but it won’t matter. I should pay attention to Cuda 9.0 instead of the default cuda10. Although used in docker does not affect the results, some contestants may need to export the configuration files of the original environment in non-docker.
(GPU should be officially approved)
This will be more similar to Aicrowd’s execution environment, and when evaluating,
docker run \
--env OTC_EVALUATION_ENABLED=true \
--network=host \
-it obstacle_tower_challenge:latest ./run.sh
Should add attributes
--runtime=nvidia
This allows you to use the nvidia driver in docker, will automatically apply cuda in docker.
In addition, GCP has pre-configured the nvidia runtime docker for you. If you are configuring in a non-GCP environment, you should refer to this.
Another special reminder is that
The newline symbol for the Dos file is ^J^M
The newline symbol for Unix files is ^J
So in some cases you will encounter bash problems, because it is the relationship of the Windows environment configuration file, you should use Vim and other similar editors to change the encoding.
In addition, can you ask the administrator to give me more quota? 
Number of available submissions
About 1 year ago Submission failed : The participant has no submission slots remaining for today.
```
I have waited for almost two days without quotas.
https://gitlab.aicrowd.com/ChenKuanSun/obstacle-tower-challenge/issues/30Announcement: Debug your submissions
About 1 year agoIf I successfully test the completion environment, I should provide repo to you so that you can publish other methods like Readme.md to help other contestants.
@arthurj
Announcement: Debug your submissions
About 1 year agoAlso in
A note should be added to the evaluation section: using nvidia-gpu should be added --runtime=nvidia
Announcement: Debug your submissions
About 1 year agoI recently discovered that your evaluation environment uses nvidia/cuda:9.0-cudnn7-runtime-ubuntu16.04. For some people (including me) it is possible to use Cuda-10. After several tests, I learned the actual environment of aicrowd, and adjusted it to cuda 9.0 when creating images on GCP.
Announcement: Debug your submissions
About 1 year agoMy question is, do you have Git LFS when you are doing a clone action to build an evaluation environment? What I am worried about is that once the evaluation environment does not use LFS clone I have a file that uses LFS, it will not be accessed correctly.
@mohanty
Announcement: Debug your submissions
About 1 year agoJust the GCP has a mechanism for providing direct import into the image. You can consider doing this and you can also make specifications.
Announcement: Debug your submissions
About 1 year agoWhat I want to know is whether there is a basic configuration that provides a similar test environment. I want to do the simulation environment on my own GCP. This way I don’t have to take up resources, and then I can adapt the configuration file and submit it.
It seems that I have tested successful files on the official docker and cannot do it in your environment.
Announcement: Debug your submissions
About 1 year agobut Sorry, I seem to test too many times, resulting in a maximum number of submissions.
Announcement: Debug your submissions
About 1 year agoThank you for developing this API for us, this is great.
Submission Failed: Evaluation Error
About 1 year agoI have the same problem, I just want to build tensorflow-gpu in docker, run the environment of dopamine framework. There have been problems all the time. Can you provide a suggested configuration file? I can already complete the 7th to 9th floors, but unfortunately I have been unable to submit successfully.
Google Dopamine on Windows
About 1 year agoMy approach is to remove the gin frame and then just call the dopamine class and so on.
Where is trained model?
About 1 year agoif you choice default setting “/tmp/dopamine”
when VM have some time do nothing, tmp/file will be delete
you should type --base_dir="./model_save/" instead of “/tmp/dopamine”
btw, you should typed “screen -S XXXX” before your training
Youtube
About 1 year agoyou can consider this
https://sites.google.com/view/struct2depth
maybe useful for you~
Not install packages due to an EnvironmentError: [Errno 28] No space left on device
About 1 year agoMy file has no problem with Gitlab (maximum limit of 10G), but when I submit it, there seems to be a lack of space for instantiation.
Submissions are stuck
9 months ago+1
my last version not in QUEUE…
https://gitlab.aicrowd.com/wywarren/obstacle-tower-challenge/tags/v5.0
Upload at 14:30