
Badges
Activity
Challenge Categories
Challenges Entered
Sample-efficient reinforcement learning in Minecraft
Latest submissions
A new benchmark for Artificial Intelligence (AI) research in Reinforcement Learning
Latest submissions
See Allfailed | 5368 | ||
graded | 4706 | ||
graded | 4702 |
Participant | Rating |
---|
Participant | Rating |
---|
Unity Obstacle Tower Challenge


Git push over 50mb
About 6 years agohttps://gitlab.aicrowd.com/Petero/obstacle-tower-challenge/issues/54
Evaluation Logs (Debug Mode)
This is a debug mode to test out your submission in AICrowd environment, the actual scores for this submission will not be reflected back to leaderboard.
State : Evaluation Pending
Total Execution Time: 9919s
Pod Health
Pod State : Pending
Pod Scheduling Time
: 9530 secs
Containers Waiting
: redis-server,aicrowd-subcontractor

Git push over 50mb
About 6 years ago(post withdrawn by author, will be automatically deleted in 24 hours unless flagged)


Git push over 50mb
About 6 years agoHi, Mohanty. There is the “pending” problem again.
Evaluation Logs (Debug Mode)
This is a debug mode to test out your submission in AICrowd environment, the actual scores for this submission will not be reflected back to leaderboard.
State : Evaluation Pending
Total Execution Time: 12634s
Pod Health
Pod State : Pending
Pod Scheduling Time
: 12135 secs
Containers Waiting
: redis-server,aicrowd-subcontractor

Git push over 50mb
About 6 years agoHow can I push a file over 50mb?
During the submission.
I got an error when I restore my model.
Message type "tensorflow.MetaGraphDef" has no field named "version"..
This problem is rare.I google it and has little result.But the model runs fine in the GCP. I try many way to figure out. Finally I try not use the “git lfs” but normal git push the .meta file and problem solved.
Then I got another error:
not an sstable (bad magic number)
and I tried to normal git push the other model files. Lots of them was pushed. Except a file about 81mb.
When I push it. Shows the error
fatal: pack exceeds maximum allowed size.
I use git lfs, and submission failed. It shows
Checksum does not match:
I google it , Lots of people tell the error occurred by using the wrong file.
I can run my model on GCP. So I think it is just occurred by the git lfs.
I google it, use the
git config http.postBuffer 52428800 git config -l
not useful.And I can’t find any place to change the limit.
There is someone can help me solve this problem?

Evalutation error : Unity environment took too long to respond
Over 6 years agoFinally, When I uninstalled the CUDA 10.0 and installed the 9.0. Problem solved.

Evalutation error : Unity environment took too long to respond
Over 6 years agoGCP tensorflow-gpu==1.13.0 gpu nvidia p100 still have same problem.

Evalutation error : Unity environment took too long to respond
Over 6 years agohi,I have same problem.
and I use the AWS.ec2.
UnityTimeOutException Traceback (most recent call last)
in ()
----> 1 env = ObstacleTowerEnv(’/home/ubuntu/ObstacleTower/obstacletower’, retro=True)
~/anaconda3/lib/python3.6/site-packages/obstacle_tower_env.py in init(self, environment_filename, docker_training, worker_id, retro, timeout_wait, realtime_mode)
~/anaconda3/lib/python3.6/site-packages/mlagents_envs/environment.py in init(self, file_name, worker_id, base_port, seed, docker_training, no_graphics, timeout_wait)
67 )
68 try:
—> 69 aca_params = self.send_academy_parameters(rl_init_parameters_in)
70 except UnityTimeOutException:
71 self._close()
~/anaconda3/lib/python3.6/site-packages/mlagents_envs/environment.py in send_academy_parameters(self, init_parameters)
489 inputs = UnityInput()
490 inputs.rl_initialization_input.CopyFrom(init_parameters)
–> 491 return self.communicator.initialize(inputs).rl_initialization_output
492
493 def wrap_unity_input(self, rl_input: UnityRLInput) -> UnityOutput:
~/anaconda3/lib/python3.6/site-packages/mlagents_envs/rpc_communicator.py in initialize(self, inputs)
78 if not self.unity_to_external.parent_conn.poll(self.timeout_wait):
79 raise UnityTimeOutException(
—> 80 “The Unity environment took too long to respond. Make sure that :\n”
81 “\t The environment does not need user interaction to launch\n”
82 “\t The Academy and the External Brain(s) are attached to objects in the Scene\n”
UnityTimeOutException: The Unity environment took too long to respond. Make sure that :
The environment does not need user interaction to launch
The Academy and the External Brain(s) are attached to objects in the Scene
The environment and the Python interface have compatible versions.
How to show the Media?
About 6 years agoHi, I’m curious about how to show the Media in my submission?
And another thing. After I answered Teri Pierce’s email. I didn’t receive any reply. Does that mean I have been eliminated?