Zoom Logo

PCG Workshop at FDG 2021 - Shared screen with speaker view
Matthew Guzdial
37:02
12!! đź’Ą
Jialin Liu
37:08
Maybe Maren can turn on recording as well? In case that I fail asleep at 1am or 2am?
Matthew Guzdial
37:21
12 submissions for the twelfth year as it’s growing linearly.
Christoph Salge
37:25
http://www.pcgworkshop.com/schedule.php
Maren Awiszus
38:08
@Jialin I can only stop the recording, it seems we can't record both at the same time
Jialin Liu
38:29
Ok I see
Jialin Liu
38:38
I will take some tea later :)
Maren Awiszus
41:29
The voice channel is on the same category as the pcg-2021 text channel
Adam Smith
44:46
Where can we find the pdfs for this workshop?
Matthew Guzdial
45:45
Not all are online yet (I think), but this one is at https://arxiv.org/abs/2107.12524
Jialin Liu
45:54
Papers will be available here: http://www.pcgworkshop.com/database.php Apologies that we did not put them online earlier
Rogério de Leon Pereira
46:10
Thanks
Matthew Guzdial
59:38
*claps*
Matthew Guzdial
59:42
Nicely done Bowei!
Jialin Liu
59:46
Excellent work!
Rogério de Leon Pereira
01:00:03
Really interesting job, thank you for the presentation.
Chengpeng Hu
01:00:24
any workflow for generating these rooms with MdMC? I am not sure if i missed something, i do not see , how ensemble method works
Adam Newgas
01:00:29
doesn't splitting up the data horizontally and vertically reduce the amount data available for training and lead to worse models?
Isaac Karth
01:02:22
Thanks!
Jialin Liu
01:02:42
Maybe the two models can be trained simultaneously in some way so that their cooperation ability (decide which model to be used next to generate a room and the accessibility) can be evaluated as well?
Phil Carlisle
01:05:52
Bowei: I'd recommend looking at maybe using a GraphRNN approach (pytorch has a graphRNN library now), so you can capture longer term inputs in a general graph structure.
Chengpeng Hu
01:06:53
thx!
Emily Halina
01:07:26
Thank you Bowei!
Matthew Guzdial
01:07:26
Thanks for the comments and questions all. Notably, the important thing was not to create the perfect Mega Man level, but just to test Ensemble Learning.
Rogério de Leon Pereira
01:07:34
Are you going to record all at once or one record for each presentation?
Jialin Liu
01:07:38
Sure! Great to see ensemble learning here!
Matthew Guzdial
01:07:40
Definitely agree that there are better models for Mega Man!
Matthew Guzdial
01:20:59
Can hear it!
Zisen Zhou
01:21:06
I can hear it too!
Rogério de Leon Pereira
01:21:10
So many awesome papers from University of Alberta. I think I should make you guys a visit soon.
Matthew Guzdial
01:21:18
Please do!
Kynan Sorochan
01:21:19
do it!
Rogério de Leon Pereira
01:21:29
It is not that far from Winnipeg
Matthew Guzdial
01:22:12
This paper is here: https://arxiv.org/pdf/2107.12533.pdf
Rogério de Leon Pereira
01:23:25
Are you from ASGAARD lab?
Matthew Guzdial
01:23:39
Nope, that’s Cor-Paul’s. I’m the advisor of this lab.
Rogério de Leon Pereira
01:24:18
Can you share your lab’s webpage, please?
Matthew Guzdial
01:24:47
One doesn’t exist, sorry. Entirely my fault for not putting one together yet.
Rogério de Leon Pereira
01:26:35
If yours is this one: http://guzdial.com/ I will reach out after the conference.
Matthew Guzdial
01:26:50
That’s my (out of date) website, yes!
Jialin Liu
01:27:18
@Matthew Are those papers based on UG students’ final year projects or the student projects in the module you teach?
Matthew Guzdial
01:27:39
Neither, just students who wanted to do research!
Jialin Liu
01:27:50
Creative and motivated students!
Matthew Guzdial
01:28:02
For sure! UofA students are fantastic.
Matthew Guzdial
01:36:26
Nice job Zisen!
Rogério de Leon Pereira
01:36:32
Have you run any statistical tests to check if there is a statistically significant difference between the three approaches?
Rogério de Leon Pereira
01:40:33
Did you run any kind of test, like and ANOVA test to see if the p-value is less then 0.05?
Rogério de Leon Pereira
01:40:58
*an ANOVA
Rogério de Leon Pereira
01:41:00
Thank you!
Zisen Zhou
01:41:41
Thanks for listening!
Emily Halina
01:41:45
Thank you for the presentation Zisen!
Phil Carlisle
01:41:48
Thanks
Rogério de Leon Pereira
01:42:12
Great presentation Zisen.
Bowei Li
01:42:37
Thank you for the presentation!
Gabriel Recchia
01:48:24
We can still hear you
Phil Carlisle
01:48:26
Can still see it ok
Maren Awiszus
01:48:27
we can hear you
Matthew Guzdial
01:48:29
You’re a little robot-y, but it’s fine
Zisen Zhou
01:48:44
There’s a bit lag, but its file
Zisen Zhou
01:48:51
*fine
Phil Carlisle
01:51:21
Now he's gone :)
Phil Carlisle
01:51:30
It was getting too exciting :)
Rogério de Leon Pereira
01:51:45
He created the hype and left, that is not fair, lol
Boris
01:52:38
the hype :D
Phil Carlisle
01:52:45
Can we get a link to the paper posted in chat?
Christoph Salge
01:53:29
https://arxiv.org/abs/2107.02457
Rogério de Leon Pereira
01:53:43
Merci
Sebastian von Mammen
01:53:57
Great session so far. Sorry that I have to leave already. đź‘Ź
Emily Halina
01:54:00
Thank you for the paper link, this work seems quite interesting!
Phil Carlisle
01:55:06
Sounds sensible
Rogério de Leon Pereira
01:55:15
That would work for me.
Jialin Liu
01:55:26
10:35
Phil Carlisle
01:55:31
What time is it now for reference?
Christoph Salge
01:55:33
meeting break 10:35
Maren Awiszus
01:55:45
10 minute break
Zisen Zhou
01:55:46
đź‘Ť
Phil Carlisle
01:55:49
:)
Rogério de Leon Pereira
01:55:58
Are you going to pause the recording?
Rogério de Leon Pereira
02:05:09
Wellcome back JP
Rogério de Leon Pereira
02:10:22
Merci beaucoup JP, great presentation. Your work is really interesting.
Emily Halina
02:10:47
Really great presentation and interesting work Jean-Baptiste!
Gabriel Recchia
02:12:17
Reasonable for this kind of exploratory work
Gabriel Recchia
02:12:25
to just report p-values as is I think
Peter Mawhorter (he/him)
02:15:11
(I agree the approach isn’t totally unreasonable, but I think multiple-comparisons corrections should be used whenever possible; it’s just something that not everyone knows to try)
Antonios Liapis
02:17:12
I use the Bonferroni correction for t-tests, when doing multiple comparisons. How do you correct multiple-corrections for correlation critical values, Peter? Maybe post in the discord for persistence?
Peter Mawhorter (he/him)
02:17:36
Sure, I’ll post on discord
Rogério de Leon Pereira
02:17:45
Good idea Liapis
Zisen Zhou
02:19:02
Thank you for the talk Jean-Baptiste!
Jialin Liu
02:19:07
Merci beaucoup Jean-Baptiste
Jialin Liu
02:21:15
The sound works well. Thank you!
Peter Mawhorter (he/him)
02:34:46
Really cool stuff! Have you considered what skip-grams might look like in this context?
Rogério de Leon Pereira
02:34:50
Thank Colan, it was a great presentation.
Emily Halina
02:35:15
Thank you for the presentation Colan! Towards the beginning of the presentation, you mentioned that n-gram approaches are effective at capturing the "style" of a level / game: would you be able to elaborate on what you mean by style here?
Adam Newgas
02:35:51
I couldn't follow how truncation preserves the level quality? doesn't that break some n-grams?
Emily Halina
02:36:39
That would be great, thanks for the explanation Colan!
Colan Biemer (he/him)
02:37:07
n-grams harry potter: https://bi3mer.github.io/blog/post_22/index.html#year=2019
Rogério de Leon Pereira
02:40:31
@Colan: If I got it right, you used some metrics like the number of spikes and other stuff to check if the level is difficult or not. Have you let real players play it and check if they agree with your measurements about how difficult the level was?
Peter Mawhorter (he/him)
02:40:40
(Wave-function collapse is actually somewhat similar to multi-dimensional N-grams...)
Colan Biemer (he/him)
02:42:26
@Rogerio, it was something we wanted to do and discussed but wasn’t really possible given the pandemic. We are planning to do something with real players down the line when we use the segments for future work
Rogério de Leon Pereira
02:43:28
Awesome, thanks Colan. Great presentation by the way.
Matthew Guzdial
02:48:01
Screen froze for me, anyone else?
Zisen Zhou
02:48:10
+1
Matthew Guzdial
02:48:18
Oh it came back
Emily Halina
02:48:19
unfrozen now for me
Johor Jara
02:48:52
it was like 3 seconds but is good now
Isaac Karth
02:54:15
Happy to see tools for scene integration, since that's a powerful part of the algorithm that has previously been somewhat intimidating for non-experts.
Hendrik Boom
02:56:45
Where is the paper?
Peter Mawhorter (he/him)
02:56:47
Very cool stuff! Thanks for the talk.
Jim Whitehead
02:56:52
Really nice work!
Matthew Guzdial
02:57:01
Thanks for the talk!
Bowei Li
02:57:03
Thanks for the great presentation!
Rogério de Leon Pereira
02:57:10
Great talk Adam, thank you.
Isaac Karth
02:57:14
Have you considered interactive methods of adding constraints? (eg. the user being able to click on bad matches to add that as a negative constraint)
Rogério de Leon Pereira
02:58:47
“Example-Based Model Synthesis”
Rogério de Leon Pereira
02:58:58
https://paulmerrell.org//model_synthesis.pdf
Peter Mawhorter (he/him)
02:59:51
The conference vs. GitHub factor is real I think!
Matthew Guzdial
03:00:00
Very gif-able as well.
Peter Mawhorter (he/him)
03:00:03
I at least saw WFC outside of academia first
Isaac Karth
03:00:13
I'm also not a fan of the WFC name
Rafa Bidarra
03:00:27
well, Paul's work on MS was pretty much impactfull at its time...
Emily Halina
03:02:38
Coffee break! :)
Rogério de Leon Pereira
03:41:55
Are we back?
Rogério de Leon Pereira
03:42:46
Patapoon….
Matthew Guzdial
03:51:15
A lot of metrics discussion at the workshop this year, interesting!
Arash Moradi
03:52:57
^+1Maybe it is time to blow the dust of the expressive range papers !
Matthew Guzdial
03:55:26
There’s been some pretty cool expressive range follow-ups I think! Mike Cook’s Danesh, and Adam Summerville’s use of e-distance to compare original data distributions and output content distributions.
Matthew Guzdial
03:57:00
Great job Emily!
Rogério de Leon Pereira
03:57:14
Great presentation.
Arash Moradi
03:57:20
Thanks Matthew, I will look into them!
Zisen Zhou
03:57:25
Thank you for the presentation Emily, nicely done!
Jim Whitehead
03:57:30
Really interesting work, great to see work on rhythm game generation!
Rogério de Leon Pereira
03:57:47
I agree Jim
Isaac Karth
03:58:11
I'd like to see even more expressive range followup, and Adam Summerville's "Expanding Expressive Range" should be part of that.
Isaac Karth
03:58:28
Thanks for the presentation!
Christoph Salge
03:58:53
I added expressive range and metrics to possibel discussion topics.
Rogério de Leon Pereira
03:58:57
Good question Maren.
Rogério de Leon Pereira
03:59:41
Maybe a next step would be let people play it and evaluate their feedback.
Arash Moradi
04:01:28
Can I have the link to the Discord server?
Christoph Salge
04:02:08
https://docs.google.com/document/d/1PpVsUcSmmfXgB4G9umC6FnDqj4IiEOYzRe2nS0CXtPM/edit?usp=sharing
Rogério de Leon Pereira
04:02:29
Alberta is rocking this year!
Matthew Guzdial
04:02:43
@Arash the link should be in your email if you’re registered for FDG
Emily Halina
04:02:43
https://arxiv.org/abs/2107.12506 (arxiv link to taikonation!)
Thomas Ball
04:03:23
One of my favorite Apple II games!
Matthew Guzdial
04:03:23
I should have linked that, sorry Emily!
Matthew Guzdial
04:03:28
Link to Kynan’s paper https://arxiv.org/abs/2107.12532
Ross Mawhorter
04:18:53
It seems like the player path would be highly dependent on the position of enemies... Is there a way to condition either the LSTM's generated path with enemy positions from MdMC, or influence the MdMC's enemy placement using the LSTM path? Also, what about placing the ladder that appears once the player collects all the gold?
Matthew Guzdial
04:18:55
Nice job Kynan!
Rogério de Leon Pereira
04:18:57
Nice presentation, thank you Kynan.
Bowei Li
04:19:19
Thanks Kynan, very interesting work and results
Isaac Karth
04:19:29
Thanks for the presentation!
Emily Halina
04:19:33
Thanks for the presentation Kynan!
Zisen Zhou
04:19:51
Thanks for the presentation!
Isaac Karth
04:22:50
I think we're due for a conversation about metrics.
Phil Carlisle
04:23:00
I agree, I want to discuss metrics
Nathan Partlan
04:23:49
Thanks, all presenters + organizers!
Christoph Salge
04:32:54
https://docs.google.com/document/d/1PpVsUcSmmfXgB4G9umC6FnDqj4IiEOYzRe2nS0CXtPM/edit?usp=sharing
Peter Mawhorter (he/him)
04:41:20
I agree that any metrics that touch on affordances rather than relying directly on raw level (or other) data are usually good ones?
Isaac Karth
04:44:51
Adam Summerville's "Expanding Expressive Range" is another one.
Isaac Karth
04:45:12
I agree it is a chicken-egg problem.
Peter Mawhorter (he/him)
04:45:57
Yeah, similarity or diversity metrics won’t be *directly* comparable between domains…
Maren Awiszus
04:46:05
I feel it's also still difficult to figure out how to model more nebulous concepts like "This level is fun" or "This level looks nice" … is this even what we want to model?
Peter Mawhorter (he/him)
04:46:24
But at least if two papers are both using versions of those we can get some indirect sense of performance?
Jim Whitehead
04:47:20
In software engineering there is a lot of focus on metrics. When determining which metrics to use in a new area, a widely used approach is "Goal - Question - Metric" or "GQM" for short.
Jim Whitehead
04:47:21
https://en.wikipedia.org/wiki/GQM
Peter Mawhorter (he/him)
04:48:12
Thanks for the link Jim, that looks interesting!
Jim Whitehead
04:48:24
The general idea is to start with high level goals on what you're trying to achieve, then translate that into more precise questions, and then metrics are used/developed to provide information which can answer those questions.
Jim Whitehead
04:49:08
Or, another way to look at it is to do a kind of requirements phase first, then use that to guide metrics selection.
Matthew Guzdial
04:50:18
“Controllability” is how this problem has been talked about in some prior work
Isaac Karth
04:50:35
Or the one I heard about this week: is the note in the same font as is used by the hospital that we've seen a lot of cases from.
Peter Mawhorter (he/him)
04:51:13
@Isaac I think I saw that article too :/
Phil Carlisle
04:51:38
The commercial games industry used to use Metacritic scores as their measure of success
Maren Awiszus
04:52:29
Regarding Playability as a metric: This assumes we have access to a human-like solver for all of our games though right?
Peter Mawhorter (he/him)
04:53:13
@Maren yeah that can be a barrier in some domains, although often it doesn’t need to be very human-like in order to be successful
Matthew Guzdial
04:53:25
That’s Mario for many of us Adam.
Phil Carlisle
04:53:56
A lot of machine learning advances are driven by relatively small improvements on standard datasets.
Isaac Karth
04:54:01
Ah, we can solve the metrics and the scicom problems with one stone by releasing our algorithms as games and evaluate them based on the Metacritic score :P
Matthew Guzdial
04:54:08
And people get annoyed about it (see Christoph’s joke-y comment about being glad Emily’s work wasn’t just platformers)
Ross Mawhorter
04:54:21
It seems like it would be hard to evaluate how well the Taiko drum model performs on mega man levels though :3
Phil Carlisle
04:54:23
I do wonder if some of that is a bit of a problem though, being focussed on a specific dataset score maybe misses the point?
Matthew Guzdial
04:54:48
“Used to be” jeez Christoph
Matthew Guzdial
04:57:01
+1 Christoph
Hendrik Boom
04:57:42
Can there be a metametric to evaluate metrics?
Ross Mawhorter
04:58:20
I've been working on Super Metroid recently, and adding different powerups that alter player movement abilities makes it hard to apply some of the Mario work
Ross Mawhorter
04:58:38
for example, a lot of papers on Mario use player position as a proxy for player state
Phil Carlisle
05:00:09
It'd be nice to see more ablation studies in PCG
Adam Newgas
05:00:11
Mario Maker games often lean very heavily on the various powerup states to make the levels interesting
Peter Mawhorter (he/him)
05:00:18
Expressive range analysis is only as good (or maybe not always even as good) as the metrics it uses as axes though…
Peter Mawhorter (he/him)
05:00:53
@Phil yeah that’s a good idea, but of course one usually uses metrics to compare ablated versions to the original… :/
Matthew Guzdial
05:00:56
@Hendrik I’d check out Adam Summerville’s paper on e-distance (Expanding Expressive Range)
Isaac Karth
05:01:41
There's probably room for a survey comparing different existing algorithms against new metrics
Phil Carlisle
05:02:06
Yeah, more survey papers maybe useful in the field?
Isaac Karth
05:02:49
Even just a working corpus of a lot of different generators would be useful, so we can compare with past work more easily
Phil Carlisle
05:03:15
Isaac: yes, that would definitely help. Having a PCG model zoo :)
Matthew Guzdial
05:04:09
Gotta make our PCG systems gif-able!
Phil Carlisle
05:04:24
I work in video generation, so yes youtube :)
Isaac Karth
05:04:38
Maybe the PCG workshop should add a SciCom element?
Zisen Zhou
05:05:21
Every academic should be animators on youtube :)
Matthew Guzdial
05:05:27
A GDC session kind of already exists with Emily Short’s Experimental AI session (running for 2 years now)
Phil Carlisle
05:05:31
hehe.. why not eh?
Maren Awiszus
05:07:15
The problem with putting a lot of work into a video presentation: As a PhD student, you get nothing out of it as it doesn't really count towards your publications towards getting your PhD. At least for me it sadly doesn't count
Matthew Guzdial
05:07:22
There’s a lot of variety there, Ubisoft La Forge, EA’s Seeds, Unity ML, etc.
Matthew Guzdial
05:07:58
Reminder for those who pre-recorded their presentations: you can and should just make them public on YouTube and link to the paper in the description.
Matthew Guzdial
05:08:09
That way it’s no more work than the conference presentation.
Maren Awiszus
05:08:20
+1 Matthew
Isaac Karth
05:08:20
Seconding Maren's point, as a field we need to reward Science Communication more.
Isaac Karth
05:08:29
+1 Matthew
Rogério de Leon Pereira
05:08:44
+1 Matthew
Peter Mawhorter (he/him)
05:08:45
Academia simply does not reward that work at all...
Isaac Karth
05:08:53
Maybe the metrics we should be talking about are the tenure committee metrics.
Matthew Guzdial
05:08:53
I think this is happening now Christoph. I don’t think we need to wait 20 years.
Phil Carlisle
05:08:56
I've found recently that a lot of companies are definitely on board. But there's still a lot of inertia
Matthew Guzdial
05:09:11
@Peter, it depends where you’re at. I get points towards tenure for science communication.
Peter Mawhorter (he/him)
05:09:13
It would have been probably 2-10x more work for me to create a really good explainer video, with animations etc., compared to the video I did produce for this conference...
Jim Whitehead
05:09:19
I also think it's important to reach out and talk to people in industry about this. Those of us who have game degree programs have alumni networks we can reach out through to make these connections.
Peter Mawhorter (he/him)
05:09:21
@Matthew that’s awesome!
Phil Carlisle
05:09:45
Townscaper does some of that right?
Jialin Liu
05:09:46
A good chance to ask the questions in this panel session: https://aingames.cn/ieeecis-sa/
Jialin Liu
05:10:05
Panel session :"Academia or industry? Why I decided to work in game industry." By speakers from game industry
Rogério de Leon Pereira
05:10:25
Awesome, thanks for sharing Jialin.
Jialin Liu
05:10:42
I will definitely ask the people from game industry about how they thing about PCG and related topics.
Adam Newgas
05:10:58
+1 on just putting the slides and voiceover out
Isaac Karth
05:11:03
Plus _you_ don't need to make all of the presentations.
Jim Whitehead
05:11:07
As well, people like Luke Dicken, who leads a design-focused game AI team within Zynga see part of their role as bridging academia and industry. He'll be here for the main conference, and Zynga will also have a GatherTown room where you can talk to Luke and other Zynga folks (most of whom came from academia and have attended FDG before starting to work for Zynga).
Adam Newgas
05:11:18
Don't compare yourself to those top science explainers with millions of views
Phil Carlisle
05:11:35
I'm from the games industry and became an academic. But I think Christoph is right, there's still a lot of inertia and buy-in for AI and PCG in general needed.
Isaac Karth
05:12:14
The transcript is somewhere in the zoom options
Isaac Karth
05:12:28
I think click the three dots button?
Jialin Liu
05:12:43
@Phil: what made you decide to became an academic, if I may ask?
Jean-Baptiste Hervé
05:13:35
Could one solution be to experiment more with mods and less with "homemade" solution? This could be a way to have more "appealing" content to showcase, while also sergin as a proof that modern game engine can run complex AI solution.
Jean-Baptiste Hervé
05:13:47
serving*
Peter Mawhorter (he/him)
05:13:55
@Jean-Baptiste yeah that makes sense
Jialin Liu
05:14:20
At the same time, we want the game engine and data from industry :)
Matthew Guzdial
05:14:44
I’m NDAed or I would offer a few counter examples.
Phil Carlisle
05:15:18
Yeah, indies are definitely on board
Jean-Baptiste Hervé
05:15:30
@Jialin I wish we had the data too... But regarding the game engines, a fair amount of games are built with Unreal Engine now
Ross Mawhorter
05:15:31
One related thing: the popularity of randomizers for old games like A Link to the Past and Super Metroid have influenced some new games coming out to add similar game modes
Ross Mawhorter
05:15:41
e.g. Bloodstained
Matthew Guzdial
05:16:11
ProcJam has a number of great Unity tutorials as well.
Phil Carlisle
05:16:27
I'd second that, yes people want to drop in solutions first and experiment second
Matthew Guzdial
05:16:29
So clearly the solution is to force Mike Cook to make tutorials for all our approaches :)
Isaac Karth
05:18:18
The Games in AI YouTube channel that Tommy Thompson runs is another example of useful communication
Rogério de Leon Pereira
05:20:03
Metrics are important, because we need something to measure and compare, but because we are talking about games, it is also important to have feedback from players to make sure we are delivering something fun to play. Talking about “quality” and “fun”, maybe it is possible to adapt the System Usability Scale (SUS) for games, and that could help to evaluate the results in the players’ perspective.
Maren Awiszus
05:20:11
Is this at some point too much to ask of one person? Should we researchers also be the ones to make the YouTube videos or would it be better to work together with someone who does that professionally? Would that even work for academia?
Isaac Karth
05:21:02
I know that some grants include funding for science communication.
Phil Carlisle
05:21:22
I'd recommend the paper Meta-Sim2 by someone from Sanja Fidlers lab and NVIDIA, where they use computer vision and RL to build procedural scenes for automated driving in Unreal Engine
Matthew Guzdial
05:22:18
Thanks for the great workshop organizers!
Zisen Zhou
05:22:26
I think if all we want is to promote paper via youtube, researchers are capable enough to make a ~1min short video to just demonstrate quickly how the system works
Zisen Zhou
05:23:21
and I find people have a tendency to click on short videos because they are not costing a lot of times
Ross Mawhorter
05:23:31
the pcgworkshop website still doesn't have a link to the schedule :3
Matthew Guzdial
05:23:43
That’s not true Ross.
Isaac Karth
05:23:47
I think it does?
Colan Biemer (he/him)
05:23:53
i can see the schedule
Phil Carlisle
05:23:54
Yeah, I see it :)
Isaac Karth
05:24:01
http://www.pcgworkshop.com/schedule.php
Maren Awiszus
05:24:49
+1 on more demos :)
Phil Carlisle
05:25:36
Tom Betts did some great talks
Phil Carlisle
05:25:47
and Oscar the guy who wrote Townscaper?
Hendrik Boom
05:25:48
Here's my river network generator; http://topoi.pooq.com/hendrik/rivers/
Phil Carlisle
05:26:19
Thanks Hendrik
Peter Mawhorter (he/him)
05:26:21
@Hendrik thanks for the link! I’m working on something similar right now so I’ll check that out
Emily Halina
05:26:45
Thanks for the workshop everyone! It was a great experience
Zisen Zhou
05:26:46
Thanks for organizing the workshop!
Jim Whitehead
05:27:03
Huge kudos to the organizers. Super successful workshop!
Kynan Sorochan
05:27:06
Thank you all so much!
Jialin Liu
05:27:08
Thank you Christoph !
Colan Biemer (he/him)
05:27:11
Thank you all!
Phil Carlisle
05:27:11
Thanks everyone!
Jialin Liu
05:27:19
Thank you all!
Rogério de Leon Pereira
05:27:20
Great workshop, thank you all.
Isaac Karth
05:27:23
Thanks to all the organizers!
Bowei Li
05:27:25
It’s been such a great experience. Thank you!
Matthew Guzdial
05:27:29
Thanks all!
Akash Saravanan
05:27:34
Thank you everyone! It has been a great experience!
Phil Carlisle
05:27:35
Thanks to all the organizers!