Loading
4 Follower
2 Following
anssi

#### Organization

Microsoft Research

GB

3
2
2

Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Mon
Wed
Fri

Loading...

Loading...

#### Challenges Entered

##### NeurIPS 2022: MineRL BASALT Competition
By MineRL Labs

Learning From Human-Feedback

#### Latest submissions

 failed 196478 Mon, 8 Aug 2022 21:24:31 failed 196122 Mon, 25 Jul 2022 17:40:24 failed 196036 Fri, 22 Jul 2022 19:38:54
##### NeurIPS 2021 - The NetHack Challenge
By AIcrowd

ASCII-rendered single-player dungeon crawl game

#### Latest submissions

 graded 163412 Sat, 30 Oct 2021 20:52:57 graded 162954 Fri, 29 Oct 2021 17:58:52 graded 159431 Fri, 15 Oct 2021 08:49:28
##### NeurIPS 2021: MineRL Diamond Competition
By MineRL Labs - Carnegie Mellon University

Training sample-efficient agents in Minecraft

#### Latest submissions

 graded 149932 Fri, 9 Jul 2021 18:32:20 graded 149876 Thu, 8 Jul 2021 21:14:41 failed 149858 Thu, 8 Jul 2021 14:55:18
##### NeurIPS 2021: MineRL BASALT Competition
By C.H.A.I. - UC Berkeley

Sample Efficient Reinforcement Learning in Minecraft

#### Latest submissions

 graded 150594 Wed, 21 Jul 2021 19:39:34 graded 150579 Wed, 21 Jul 2021 17:34:56 failed 150215 Thu, 15 Jul 2021 17:07:05
##### NeurIPS 2020: Procgen Competition
By OpenAI

Measure sample efficiency and generalization in reinforcement learning using procedurally generated environments

#### Latest submissions

No submissions made in this challenge.
##### The Neural-MMO Challenge
By MIT

Robustness and teamwork in a massively multiagent environment

#### Latest submissions

No submissions made in this challenge.
##### Seismic Facies Identification Challenge
By SEAM AI

3D Seismic Image Interpretation by Machine Learning

#### Latest submissions

 graded 83204 Sat, 19 Sep 2020 11:41:02 graded 82875 Wed, 16 Sep 2020 20:53:48 failed 82870 Wed, 16 Sep 2020 20:46:37
##### NeurIPS 2020: MineRL Competition
By MineRL Labs - Carnegie Mellon University

Sample-efficient reinforcement learning in Minecraft

#### Latest submissions

 graded 117319 Tue, 26 Jan 2021 10:42:32 graded 107745 Fri, 4 Dec 2020 11:24:20 graded 107322 Tue, 1 Dec 2020 12:50:48
##### NeurIPS 2019 : MineRL Competition
By MineRL Labs - Carnegie Mellon University

Sample-efficient reinforcement learning in Minecraft

#### Latest submissions

 failed 25431 Tue, 26 Nov 2019 11:49:01 graded 25415 Tue, 26 Nov 2019 09:41:03 graded 25316 Mon, 25 Nov 2019 16:34:36
##### Unity Obstacle Tower Challenge
By Unity Technologies

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

#### Latest submissions

 graded 8597 Thu, 11 Jul 2019 12:22:32 graded 8541 Wed, 10 Jul 2019 22:48:58 graded 8531 Wed, 10 Jul 2019 20:38:29
##### MakeWaterfall
By C.H.A.I. - UC Berkeley

#### Latest submissions

No submissions made in this challenge.
##### BuildVillageHouse
By C.H.A.I. - UC Berkeley

#### Latest submissions

 graded 150594 Wed, 21 Jul 2021 19:39:34 graded 150579 Wed, 21 Jul 2021 17:34:56
Participant Rating
MasterScrat 229
shivam 136
vrv 0
araffin 0
Participant Rating
shivam 136
MasterScrat 229

### Process Videos: Evaluation timed out

5 months ago

Hey! This pops up randomly. I would requeue the submission but the same bug seems to make this impossible from my end .

Can you resubmit your solution? I can remove failed solutions for you so you get submission quota back

### Debug Submission with debug=false

5 months ago

Hmm it might have not updated because the score is has not improved over the debug submission, but this is just a finnicky thing of the leaderboard.

### Debug Submission with debug=false

5 months ago

It looks like the tag for the submission was done to wrong commit indeed, triggering a submission which uses code from 3 months ago. You could try doing a tag here on the main branch (remember to start with “submission-”): AIcrowd

### Debug Submission with debug=false

5 months ago

Hey! Make sure you have pushed the changes and that you have tagged the submission after the change. If that does not help, please share the issue page of your submission so I can take a look

### Process Videos: Error (exit code 1): Unable to find metadata.json for all environments

6 months ago

Hey! Sorry about this, still looking into this . The BASALT side has gotten bit more attention as it is the main track, but now those errors are fixed for now so intro track will get some love!

### Process Videos: Error (exit code 1): Unable to find metadata.json for all environments

6 months ago

@mohanty Would you have any idea what could be bugged up here?

### [Request] Dummy data location

8 months ago

@yamato.kataoka In case you missed it, the full dataset is now available here

### [Request] Dummy data location

8 months ago

Hey. Sorry for the headache: we are just about to share the full dataset, though, which will use the same storage method as the other OpenAI VPT data they shared! That one you will be able to curl/wget easily :). Stay tuned; we will announce this on Discord and update the AICrowd main page with the link.

### "process no longer exists" error

8 months ago

Hey there! The code is running correctly, it is just closing the environment that sometimes (or always) throws an error on Windows. You can ignore this error for now. If you want code to continue after calling env.close, wrap it around try-except blocks.

### Anything news for thhe mineRL competition?

About 1 year ago

Hey. Sadly there are no news as of yet, so you have not missed anything. Stuff might now how happen now that holidays are over but I can not promise when.

### Is there anyway to know i am getting hurt during inference stage?

Over 1 year ago

Hey. There is no API to get this information in MineRL environments right now, so no. That info is just for aicrowd evaluation.

### About the duration of Round 1

Over 1 year ago

Hey. Unfortunately the tight schedule requested by NeurIPS competition board is making it a bit difficult to extend deadlines further. We will likely only extend deadline if more technical issues crop up that require more days to handle.

### How many teams will be invited this year?

Over 1 year ago

Hey! I assume this is the number of participants invited to the workshop to present their submissions etc? Ideally we would like to invite all Round 2 finalists + some from Intro track, depending on how NeurIPS workshop is structued! We will let you know when we have the exact numbers

Prizes are to be determined (but they are coming!)

### Question about timeline of research track round II

Over 1 year ago

The deadline was set to 15th October initially, but rules indeed make it sound different.

I will let Nicholay (our rules guy) answer the question for final confirmation

### Can i select dataset in any ways?

Over 1 year ago

Hey! Sorry for the delay (we are more active on the Discord server).

In Intro track, you are free to use the data in any way possible. In Research track, however, you are not allowed to have such fine-grained selection (unless it is selected by a trained neural network).

### Network problem leading fail to build image consume submission quota

Over 1 year ago

Ah! I assume you refer to the figure here? https://github.com/minerllabs/competition_submission_template (Edit: I have removed the said figure from the github page. It had text “max. 20 submissions”)

That information is wrong, and for now there are unlimited number of submissions (but with a daily cap). Thanks for pointing this out tho! I will fix it.

Failed submissions are counted as submissions as well, as long they started the building stage (this, too, takes quite a bit of resources to run).

### Network problem leading fail to build image consume submission quota

Over 1 year ago

Hey. The submission quota refreshes daily, but in a pinch @Shivam or someone else from AICrowd can requeue your submission if it fails in docker build phase (sorry, I did not notice your message on gitlab up until now).

### What is the hardware configuration of online machine for research track?

Over 1 year ago

Nope, no per-step limitations. I would recommend that the MineRL environment will work if you have very long delays between step calls (it should not matter, but easier to check locally than on the evaluation server )

### Error of running the BC baseline code

Over 1 year ago

Judging by when bc.py was added, this is the imitation version that could work.

### Error of running the BC baseline code

Over 1 year ago

Hey! Sorry for the delay!

The baseline code was tested to work during release but sadly it seems like some of the dependencies have been updated since and it breaks this code . My wild guess is that imitation repository has changed. Your best bet is to checkout older version of imitation and installing that (a manual process…).

An easier step would be to double-check you have the up-to-date library versions as specified by environment.yml, but I assume this is already the case.

anssi has not provided any information yet.