Location
KR
Badges
Activity
Ratings Progression
Challenge Categories
Challenges Entered
Completed
SNCF
SBB
Deutsche Bahn
Multi-Agent Reinforcement Learning on Trains
Latest submissions
MineRL Labs - Carnegie Mellon University
Sample-efficient reinforcement learning in Minecraft
Latest submissions
See All| failed | 11423 | ||
| graded | 11325 |
Unity Technologies
A new benchmark for Artificial Intelligence (AI) research in Reinforcement Learning
Latest submissions
See All| graded | 9084 | ||
| graded | 9083 | ||
| failed | 9072 |
AIcrowd
Multi-Agent Reinforcement Learning on Trains
Latest submissions
| Participant | Rating |
|---|
| Participant | Rating |
|---|
-
RLKR_Miner NeurIPS 2019 : MineRL CompetitionView
Unity Obstacle Tower Challenge
Performance degradation after submission
Over 5 years agoHi @arthurj
I just submitted my algorithm and it goes over 5th floor!
I think problem is solved. Thank you 
Performance degradation after submission
Over 5 years agoHello.
If I test my algorithm in my computer with Obstacle tower 2.0 version, it goes to 6~7th floor on average.
However, if I submit my algorithm, it always cannot go over 5th floor and gets sum of reward as 6.8.
When I check the leaderboard, others also seem to have lower grades than round1.
Is the environment for evaluation different from github’s environment? (https://github.com/Unity-Technologies/obstacle-tower-env)
Thank you in advance.
Episode 5 of the evaluation
Over 5 years agoI have same problem.