Loading
1 Follower
0 Following
sungbinchoi
Sungbin Choi

Location

KR

Badges

3
2
2

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

ASCII-rendered single-player dungeon crawl game

Latest submissions

No submissions made in this challenge.

Machine Learning for detection of early onset of Alzheimers

Latest submissions

No submissions made in this challenge.

Latest submissions

No submissions made in this challenge.

Robustness and teamwork in a massively multiagent environment

Latest submissions

No submissions made in this challenge.

3D Seismic Image Interpretation by Machine Learning

Latest submissions

See All
graded 109697
graded 109696
graded 109639

Latest submissions

No submissions made in this challenge.

Play in a realistic insurance market, compete for profit!

Latest submissions

No submissions made in this challenge.

A benchmark for image-based food recognition

Latest submissions

No submissions made in this challenge.

Latest submissions

See All
graded 134992
graded 134991
graded 134988

Multi-agent RL in game environment. Train your Derklings, creatures with a neural network brain, to fight for you!

Latest submissions

No submissions made in this challenge.

Predicting smell of molecular compounds

Latest submissions

No submissions made in this challenge.

Latest submissions

No submissions made in this challenge.

Latest submissions

No submissions made in this challenge.

Latest submissions

No submissions made in this challenge.

Sample-efficient reinforcement learning in Minecraft

Latest submissions

See All
graded 21062
failed 21054
failed 20945

Multi Agent Reinforcement Learning on Trains.

Latest submissions

See All
failed 24337
failed 24335
failed 24334

Latest submissions

No submissions made in this challenge.

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

Latest submissions

See All
graded 9133
graded 9132
graded 9079

Detect Multi-Animal Behaviors from a large, hand-labeled dataset.

Latest submissions

See All
graded 133162
graded 133159
graded 133110

Adapt Behavior Detectors to capture individuals' annotation style.

Latest submissions

See All
graded 134992
graded 134985
graded 134952

Learn to Recognise New Behaviors from limited training examples.

Latest submissions

See All
graded 134991
graded 134988
graded 134982
Participant Rating
jungyeon_lee 0
Participant Rating
sungbinchoi has not joined any teams yet...

Multi-Agent Behavior: Representation, Model-17508f

Claim your AWS Credits | Report your improvement in baseline score

Over 1 year ago

Team name: sungbinchoi
Submission id: 128954
F1 score on Task 1: 0.848
A brief intro about you: PhD. Deep learning enthusiast

Can we use training data from task 1 or 2 for task 3?

Over 1 year ago

Is it allowed to use models trained on task 1 or 2 train set
and then somehow finetune those models for task 3?

Can we use past or future frame for prediction?

Over 1 year ago

For example, if I’m making prediction for 100th frame,
is it allowed to utilize 99th or 101th frame’s mouse position?

Flatland Challenge

Evaluation server hardware specifications

Over 2 years ago

Is GPU available on evaluation server?
I think GPU is necessary if we want to experiment with global observation.

NeurIPS 2019 : MineRL Competition

The evaluation result does not match my local testing

Almost 3 years ago

My code is also running on TF 1.13.1.
But TF version 1.13.1 is specified on my environment.yml file.
I’m still confused about what went wrong.

The evaluation result does not match my local testing

Almost 3 years ago

I have a same problem.
Evaluation successful but only 1 episode with 4 steps.

Sample efficiency and human dataset

About 3 years ago

Let me ask another question about MINERL_TRAINING_MAX_INSTANCES = 5 in competition_submission_starter_template. I’m not quite sure how INSTANCE is defined.
Does it mean that max 5 gym env could be run in parallel while training?
Or max 5 parallel trainer perform update function independently and somehow merge gradients periodically?
Or max 5 processes (regardless of doing what kind of job) can be deployed while training?

Unity Obstacle Tower Challenge

Submissions are stuck

About 3 years ago

I think it’s stuck again.

Possible bug with tower-seed in env 2.0

About 3 years ago

Yes, I guess the bug is not fixed yet.
I’ll post a comment on that github issue link.
->
Now I got the answer.
They said tower-seed value range is intentionally limited to 100 in Round 2.

Possible bug with tower-seed in env 2.0

About 3 years ago

Although I defined specific tower-seed when I reset the environment,
random seed is assigned instead
when tower-seed >= 100.
It looks like env 2.1 has the same problem.

{first_name}.{last_name}.1@gmail.com