Badges
Activity
Ratings Progression
Challenge Categories
Challenges Entered
Completed
AIcrowd
Facebook AI Research (FAIR)
ASCII-rendered single-player dungeon crawl game
Latest submissions
Carnegie Mellon University
Arrival
The first, open autonomous racing challenge.
Latest submissions
ADDI
Machine Learning for detection of early onset of Alzheimers
Latest submissions
MIT
Robustness and teamwork in a massively multiagent environment
Latest submissions
SEAM AI
3D Seismic Image Interpretation by Machine Learning
Latest submissions
See All| graded | 109697 | ||
| graded | 109696 | ||
| graded | 109639 |
Sony Group Corporation
Latest submissions
Imperial CPG
Play in a realistic insurance market, compete for profit!
Latest submissions
Seerave Foundation
A benchmark for image-based food recognition
Latest submissions
MABe Team
Latest submissions
See All| graded | 134992 | ||
| graded | 134991 | ||
| graded | 134988 |
Dr Derk
Multi-agent RL in game environment. Train your Derklings, creatures with a neural network brain, to fight for you!
Latest submissions
Firmenich
Predicting smell of molecular compounds
Latest submissions
OpenSky Network
Cyber-Defence Campus, armasuisse
Find all the aircraft!
Latest submissions
HAC Software Inc
Latest submissions
Max Planck Institute for Intelligent Systems
Disentanglement: from simulation to real-world
Latest submissions
MineRL Labs - Carnegie Mellon University
Sample-efficient reinforcement learning in Minecraft
Latest submissions
See All| graded | 21062 | ||
| failed | 21054 | ||
| failed | 20945 |
SBB
Multi Agent Reinforcement Learning on Trains.
Latest submissions
See All| failed | 24337 | ||
| failed | 24335 | ||
| failed | 24334 |
Computer Vision Lab - ETH Zurich
Immitation Learning for Autonomous Driving
Latest submissions
Unity Technologies
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 |
|---|
Multi-Agent Behavior: Representation, Model-17508f
Can we use training data from task 1 or 2 for task 3?
10 months agoIs 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?
10 months agoFor 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
About 2 years agoIs 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
Over 2 years agoMy 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
Over 2 years agoI have a same problem.
Evaluation successful but only 1 episode with 4 steps.
Sample efficiency and human dataset
Over 2 years agoLet 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
Possible bug with tower-seed in env 2.0
Over 2 years agoYes, 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
Over 2 years agoAlthough 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.
Claim your AWS Credits | Report your improvement in baseline score
10 months agoTeam name: sungbinchoi
Submission id: 128954
F1 score on Task 1: 0.848
A brief intro about you: PhD. Deep learning enthusiast