Loading
Feedback

kyunghyunlee 70

Badges

0
1
1

Activity

Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Mon
Wed
Fri

Ratings Progression

Loading...

Challenge Categories

Loading...

Challenges Entered

A new benchmark for Artificial Intelligence (AI) research in Reinforcement Learning

Latest submissions

See All
graded 4081
graded 4069
graded 4059
Gold 0
Silver 1
Boltzmann's Favourite
May 16, 2020
Bronze 1
Trustable
May 16, 2020

Badges

  • Has filled their profile page
    May 16, 2020

  • May 16, 2020

  • May 16, 2020

  • May 16, 2020

  • May 16, 2020
  • Kudos! You've been awarded a silver badge for this challenge. Keep up the great work!
    Challenge: Unity Obstacle Tower Challenge
    May 16, 2020
Participant Rating
Participant Rating
kyunghyunlee has not joined any teams yet...

Unity Obstacle Tower Challenge

Submissions Q&A

Over 1 year ago

It seems evaluation server dead.
Mine stuck for 7 hours

Evalutation error : Unity environment took too long to respond

Over 1 year ago

In local docker, it always tested well.
I am getting same error for every submission.

The Unity environment took too long to respond.

Problem on agent

Over 1 year ago

It runs correctly in my local machines.
Also, set realtime_mode=True doesn’t help.

Testing agent in local with docker

Over 1 year ago

I followed the instruction in README.md.
I successfully built docker image.

I run docker image with tow terminals as described in Run Docker image section.
The agent looks good and it waits for the environment.
When I run the environment, anything happens.
Below are my console messages for both.

Agent

root
INFO:mlagents_envs:Start training by pressing the Play button in the Unity Editor.
Traceback (most recent call last):
  File "run.py", line 27, in <module>
    env = ObstacleTowerEnv(args.environment_filename, docker_training=args.docker_training)
  File "/srv/conda/lib/python3.6/site-packages/obstacle_tower_env.py", line 45, in __init__
    timeout_wait=timeout_wait)
  File "/srv/conda/lib/python3.6/site-packages/mlagents_envs/environment.py", line 69, in __init__
    aca_params = self.send_academy_parameters(rl_init_parameters_in)
  File "/srv/conda/lib/python3.6/site-packages/mlagents_envs/environment.py", line 491, in send_academy_parameters
    return self.communicator.initialize(inputs).rl_initialization_output
  File "/srv/conda/lib/python3.6/site-packages/mlagents_envs/rpc_communicator.py", line 80, in initialize
    "The Unity environment took too long to respond. Make sure that :\n"
mlagents_envs.exception.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.

Environment

+ ENV_PORT=
+ ENV_FILENAME=
+ '[' -z '' ']'
+ ENV_PORT=5005
+ '[' -z '' ']'
+ ENV_FILENAME=/home/otc/ObstacleTower/obstacletower.x86_64
+ touch otc_out.json
+ APP_PID=7
+ xvfb-run --auto-servernum '--server-args=-screen 0 640x480x24' /home/otc/ObstacleTower/obstacletower.x86_64 --port 5005 2
+ TAIL_PID=8
+ wait 7
+ tail -f otc_out.json

Problem on agent

Over 1 year ago

I tested the Obstacle tower environment with local machines.
I confirmed that the action space is consist of 4 numbers in list, like [0, 0, 0, 1]
I submitted a starter kit agent for a test, and it evaluated successfully.

Then, I tested my agent for submission which slightly modified from starter kit.
The modification was to force jump action 0 from env.action_space.sample()
Actual source code is below. It is part of run.py in run_episode(env) function.

while not done:
    action = env.action_space.sample()
    action[2] = 0
    obs, reward, done, info = env.step(action)

From evaluation log, it stuck at step 0.

It is my first try to participate in this kind of challenges, therefore I am not familiar with the environment.
What is the problem with my code?

Something changed in evaluation seed 5

Over 1 year ago

I read Rules once more, but still have a question.
In section 11, the definition of Average Level is based on the highest average level in the Leaderboard.
However in section 6, the Team will be evaluated based upon the last Entry they submit.

I wonder which one is correct.

Best regards,
Kyunghyun Lee

Something changed in evaluation seed 5

Over 1 year ago

Hi, I am getting average floor neer 4.6~5.4.
Before the deployment yesterday, I got that score with some randomness.
After that, I tested various weights of my model, I am continuously getting floor 2 in seed 5.

In my opinion, something must be changed with seed 5.
My concern is that the rule said team score will be evaluated based on the last submit, not in the leaderboard.
If I know something will be changed during round 1, I would not submit anymore when I reached floor 5.
I think it is unfair that some setting is changed without any notice.

I want to know your thinking about this topic.
Thank you for your support.

Best regards,
Kyunghyun Lee

Team participation

Over 1 year ago

I sent an email to OTC@unity3d.com about my team participation, but want to confirm that nothing wrong.

Below is the original message.
Is it sufficient for participating?
Are there any other things to do?

Kyunghyun Lee.

Below:

Team name: RCV

Team Member

Lead: Kyunghyun Lee
Date of Birth: 08/24/1988
Mail: damul731@gmail.com (login aicrowd with github account)
Nationality: South Korea

Member1: Wookcheol Shin
Date of Birth: 08/20/1992
Mail: shinwc159@gmail.com (login aicrowd with github account)
Nationality: South Korea

Team participation

Over 1 year ago

I sent an email to OTC@unity3d.com about my team participation, but want to confirm that nothing wrong.

Below is the original message.
Is it sufficient for participating?
Are there any other things to do?

Kyunghyun Lee.

Below:

Team name: RCV

Team Member

Lead: Kyunghyun Lee
Date of Birth: 08/24/1988
Mail: damul731@gmail.com (login aicrowd with github account)
Nationality: South Korea

Member1: Wookcheol Shin
Date of Birth: 08/20/1992
Mail: shinwc159@gmail.com (login aicrowd with github account)
Nationality: South Korea

kyunghyunlee has not provided any information yet.