Matthew Schlegel (@mattschleg) header
Matthew Schlegel (@mattschleg) profile picture

RL and ML in real world applications. PhD. Musician. Celiac. On the search for the perfect espresso. Currently working on hard things @ucalgary.

Calgary, Alberta
Joined February 2018
Photo by Matthew Schlegel (@mattschleg)Photo by Matthew Schlegel (@mattschleg)Photo by Matthew Schlegel (@mattschleg)Photo by Matthew Schlegel (@mattschleg)Photo by Matthew Schlegel (@mattschleg)Photo by Matthew Schlegel (@mattschleg)Photo by Matthew Schlegel (@mattschleg)Photo by Matthew Schlegel (@mattschleg)Photo by Matthew Schlegel (@mattschleg)Photo by Matthew Schlegel (@mattschleg)
Excited to be co-organizing the AAAI 2027 Workshop on Physics-Governed AI for Energy (PGAI4E)! We are actively seeking contributions and reviewers! See pgai4e.github.io for more details or fill out this form to be a reviewer: docs.google.com/forms/d/e/1F… #AAAI2027 #AI4Energy
160
Very excited to have contributed to this paper @icmlconf lead by @DikshantShehmar! We explore if Laplacian representations could be a linchpin for planning with learned models. This work could unlock the data efficient future often promised from model-based planning!
Here's another paper we'll be presenting at ICML'26 - @icmlconf. Laplacian Representations for Decision-Time Planning openreview.net/forum?id=6Jwk… This work was led by @DikshantShehmar, and he'll be presenting on 8th July at 2 pm, Korea time. This video summarizes the idea well ↓
2
16
1,627
At #NeurIPS2025 come check out our poster in the TCCAI workshop at 4:00pm on Sunday! In this preliminary work, we are thinking about how to apply various resolution-invariant models to power grid data to accelerate simulations with renewables! scholar.google.com/citations…
3
94
Hey! @modl_ai is pretty cool and we are doing really cool things! This is a brilliant opportunity to do a PhD with Modl and work with some really fantastic researchers! If you have any questions feel free to reach out!
Happy to announce we have an industrial PhD position available at @ITUkbh in collaboration with @modl_ai on improving automated video game testing via machine learning 🎮🐞🤖 You'll be advised by me with support from @togelius and @yannakakis. Ping me if interested!
1
5
1,344
Now that it is public! Happy to be joining Modl! Really looking forward to working with such a great team!
👋A warm welcome to Matthew to modl! He is our latest addition to our Technical Staff Team in Research with a wealth of knowledge in RL and Deep Learning, with a particular focus on agent perception. We're absolutely delighted to have you with us, @mattschleg! 🌟
3
19
866
Matthew Schlegel retweeted
Someone please start a petition to leave the main paper + supplement as one PDF for NeurIPS. This nonsense stops this year.
12
11
4
214
53,512
New paper published at TMLR in collaboration with Volodmyr Tkachuk, Adam White, and @white_martha! Done all in the @rlai_lab and @AmiiThinks labs! Check it out: openreview.net/forum?id=K6g4… To be brief, we do a deep empirical investigation on a single axis of choice in RNNs for RL.
1
3
30
2,883
To be brief: The paper provides new ideas on how to evaluate recurrent agents in the reinforcement learning domain, future potential directions in designing recurrent architectures for continual decision making (i.e. RL), and a ton more including the appendix!
3
293
On the job market! Looking for Post Docs and Research Scientist positions that will broaden my views on RL and machine intelligence! My research is centered on understanding and developing multi-prediction systems and agent-state construction in RL. CV: mkschleg.github.io/CV.pdf
1
4
24
Matthew Schlegel retweeted
just made a "decentralized" "alternative" to twitter; everyone should go "join" it to make an account: fork github.com/diracdeltas/tweet… to tweet: git commit --allow-empty to follow someone: git remote add <alias> <their fork url> to retweet: git cherry-pick <their "tweet">
35
325
110
1,420
To those submitting papers to venues that allow for paper updates in response to reviews: Please clearly mark what edits are made from the original version so reviewers can easily spot changes and provide more feedback. I mark all text in red that is different from the original.
3
In #Denver for a bit. Any recommendations for coffee shops? @5280coffeelife maybe?
You know I’m getting ready to graduate when my department’s new building is almost done 😂😂.
3
At @AmiiThinks #AIWeek2022 ? Come check out some of the work we are doing in Adam White's research group! Poster session A starts at 11:30!
1
1
21
My time has finally come to review a #TMLR paper 👀.
7
I'm starting to write my actual thesis document. Awhile ago, I saw someone work on this in public (I can't remember who unfortunately, but do tag them in the comments!) and wanted to also do this. You will be able to see my progress at github.com/mkschleg/thesis.
3
1
13
I'm using org-mode (which I used for my candidacy) and will be using that document as a starting point. This should be a fun experiment, and it will be public knowledge how sporadically I work on it 🤣.
1
1
I'm never as certain I grew up in the Midwest than when there is a tornado warning and my first instinct is to go outside to look.
4