0 Follower
0 Following
mseitzer
Location
DE
Badges
1
1
0
Activity
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Mon
Wed
Fri
Challenge Categories
Loading...
Challenges Entered
Completed
Stanford Neuromuscular Biomechanics Laboratory
Reinforcement Learning on Musculoskeletal Models
Latest submissions
Max Planck Institute for Intelligent Systems
Disentanglement: from simulation to real-world
Latest submissions
See All| graded | 21042 | ||
| graded | 21037 | ||
| graded | 21033 |
GOAL-Robots
Robots that learn to interact with the environment autonomously
Latest submissions
See All| failed | 21943 | ||
| failed | 21942 | ||
| failed | 21938 |
| Participant | Rating |
|---|
| Participant | Rating |
|---|
-
AutoLearingMPI NeurIPS 2019 - Robot open-Ended Autonomous LearningView
NeurIPS 2019 : Disentanglement Challenge
Which tag in git will you choose for final ranking?
Over 6 years agoCan you clarify this further please? What exactly is the rank? Does the best score on a metric get rank 1, second best score gets rank 2, etc?
Furthermore, do you average over all submissions, or do you just take the submission with the best scores into account?
mseitzer has not provided any information yet.
Use of labels of published datasets
About 6 years agoHi,
is it allowed to use the labels (i.e. ground truth factors) of the published datasets (mpi3d_toy and mpi3d_realistic) in any way for pretraining?
In [Announcement] Regarding Transfer Learning!, you stated that it is allowed to use any data to produce pretrained weights. Following this wording, using the labels is allowed.
Can you confirm this please?