Badges
Activity
Ratings Progression
Challenge Categories
Challenges Entered
Completed
Stanford Neuromuscular Biomechanics Laboratory
Reinforcement Learning on Musculoskeletal Models
Latest submissions
MineRL Labs - Carnegie Mellon University
Sample-efficient reinforcement learning in Minecraft
Latest submissions
Unity Technologies
A new benchmark for Artificial Intelligence (AI) research in Reinforcement Learning
Latest submissions
| Participant | Rating |
|---|
| Participant | Rating |
|---|
NeurIPS 2019 : MineRL Competition
Why you can't give an absolute dataset download link?
Over 4 years agoTrue, it is really much faster than wget the link, and I know your team’s hardworking, thanks, but the python script can cause error, I don’t know why, I just can’t change the download directory, and cause the same error over and over again.
In this case, I think people need an alternative way to get the dataset, even take the cost of a longer download time.
Issues downloading the dataset
Over 4 years agoThe lasted dataset is still the download link, right? https://router.sneakywines.me/minerl/data_texture_0_low_res.tar.gz
Why you can't give an absolute dataset download link?
Over 4 years agoWhy you can’t give an absolute dataset download link there? Why you must download the dataset by a python command? If I want to download through a single link and figure out what the link is, I should go and check the source code?
Dataset Download speed
Almost 5 years agoSo the dataset you provided which has the size of 15.3G, and I have already downloaded was in vain??
Why it is not start yet?
Almost 5 years agoIt’s time for the competition begin, but why it is not start yet? I can’t find the resource and other demo codes.
NeurIPS 2019: Learn to Move - Walk Around
Velocity target explanation
Over 4 years agoBesides, http://osim-rl.stanford.edu/docs/training/ you said cd osim-rl/examples and run ddpg.keras-rl.py but I checked, that file is in one more subfolder under-construction, so it is still under-construction that we are not allowed to run it or it will raise an error when we run it?
Velocity target explanation
Over 4 years agoBut in your document, it said converge to (2.9, 5.7), where is that location? the center point of the circle showed on the top-left picture? I think it is something like (5.7, -2.9). Then you said “the human model should locomote to the right as the vector points towards the right”, now that is right? What I can get from the bottom-left map is all the allows point to a certain point, which is roughly (0, -1), so what do you mean (0, 1)??
Winning Solution of last year's competition
Almost 5 years agook, thanks. Are you work in Baidu aha?
Unity Obstacle Tower Challenge
Evalutation error : Unity environment took too long to respond
About 5 years agoWhen I tried to set up xserver on google colab, it raised error : parse_vt_settings: Cannot open /dev/tty0 (No such file or directory)
Have you met the same error and how did you solve it
Evalutation error : Unity environment took too long to respond
About 5 years agoAnd I have tested the env in local, it worked well. But once I run the code on Google Colab, the error comes.
Evalutation error : Unity environment took too long to respond
About 5 years agoI just put the ObstacleTower folder which includes the obstacle.x86_64 file in the proper directory. Then I directly run the train.py as the tutorial says. Do I need to start the obstacle.x86_64 file manually before running the train.py?
Evalutation error : Unity environment took too long to respond
About 5 years agoI run the offical tutorial code on gcp, I have changed the timeout_wait to 6000000, but it still raise the same error, so how you fix the problem?
Submissions Q&A
About 5 years agoExcuse me, bro. There are some questions that need your help:
- How can I create a gitlab repo to submit my code, it seems that their official gitlab website can’t get access
- If I can make a submission once after I follow their “training the agent on gcp” tutorial only and run the code successfully?(except the error that:
The Unity environment took too long to respond....)
Couldn't launch the obstacletower environment
About 5 years ago(post withdrawn by author, will be automatically deleted in 24 hours unless flagged)
Couldn't launch the obstacletower environment
About 5 years agoI mean … which folder should I put it
Why you can't give an absolute dataset download link?
Over 4 years agoYes, thanks, can I ask where you track that link? I know the
lib/python3.6/site-packages/minerl/data/download.pybut even though Ipip3 install --upgrade minerlfirst, what I can hack is also thehttps://router.sneakywines.me/minerl/data_texture_0_low_res.tar.gznotminerl-v1