Marcel Müller's Avatar

Marcel Müller

@marcel-mueller

PhD student interested in #multi-agent #reinforcementlearning, #logistics, #deadlocks, and #simulation @Otto von Guericke University #Magdeburg

58
Followers
119
Following
42
Posts
14.11.2024
Joined
Posts Following

Latest posts by Marcel Müller @marcel-mueller

Preview
Generative AI for Automatic Simulation Model Generation in Factory Planning: A Framework and Prototype Manual development of simulation models in factory planning is a time-intensive task that requires domain expertise and specialized software knowledge…

Check out our new article about generative AI for automatic simulation model generation in factory planning: www.sciencedirect.com/science/arti...

19.01.2026 12:02 👍 1 🔁 1 💬 0 📌 0

There is also some big difference between the capabilities between free and paid versions

31.12.2025 03:43 👍 0 🔁 0 💬 1 📌 0

Had good experience with codex directly in vs code. Also the agentic behavior seems like the next big step even though it's hard to trust it and just let it code for you.

31.12.2025 03:41 👍 1 🔁 0 💬 0 📌 0

Thanks for sharing! Sure, always interested but sometimes it's difficult to keep up with all the new stuff.

16.11.2025 02:34 👍 0 🔁 0 💬 0 📌 0
Preview
Multi-Agent Reinforcement Learning for Deadlock Handling among Autonomous Mobile Robots This dissertation explores the application of multi-agent reinforcement learning (MARL) for handling deadlocks in intralogistics systems that rely on autonomous mobile robots (AMRs). AMRs enhance oper...

There is my thesis. :) arxiv.org/abs/2511.07071

11.11.2025 18:57 👍 1 🔁 0 💬 0 📌 1

Is there some cool app out there to easily read papers on the mobile phone? I hate to zoom into every PDF.

06.11.2025 02:34 👍 0 🔁 0 💬 1 📌 0

Cool! Thank you! I will check it out!

05.11.2025 11:43 👍 0 🔁 0 💬 0 📌 0

:_)

05.11.2025 10:06 👍 0 🔁 0 💬 1 📌 0

Any good paper recommendations for this?

05.11.2025 01:40 👍 0 🔁 0 💬 1 📌 1

I really liked that in an international context I can write to a professor with "Hi Dave". That gave me at least the illusion of a small hierarchy there. On the other hand, they give PhD students in Germany lot of responsibility as engineers. So that's fine too. Please don't distribute bad habits.

28.07.2025 01:03 👍 1 🔁 0 💬 1 📌 0

Wenn es nicht alle sind, würde ich tippen 12, 13 und 24.

12.07.2025 21:06 👍 1 🔁 0 💬 1 📌 0

Thank you very much for the comprehensive answer!!

10.07.2025 20:07 👍 1 🔁 0 💬 0 📌 0

Any tips you can share for good code documentation?

10.07.2025 00:18 👍 0 🔁 0 💬 1 📌 0

Thanks! Hopefully around October.

03.07.2025 17:49 👍 0 🔁 0 💬 0 📌 0
Multi-Agent Reinforcement Learning for Deadlock Handling among Autonomous Mobile Robots
Multi-Agent Reinforcement Learning for Deadlock Handling among Autonomous Mobile Robots YouTube video by Marcel Müller

I don’t know if it’s groundbreaking (as claimed in the podcast), but I just submitted my PhD thesis.
If you're as impatient as I am for the defense, there's already a pretty cool podcast episode about it, generated with NotebookLM:
🎧 www.youtube.com/watch?v=YlpD...

03.07.2025 16:19 👍 2 🔁 0 💬 1 📌 0

Is this a bad joke or a seek for attention? If not, please search help immediately. There is nothing more valuable than life.

30.06.2025 01:15 👍 0 🔁 0 💬 1 📌 0

Thanks for sharing!

12.06.2025 13:54 👍 1 🔁 0 💬 0 📌 0

Thanks for sharing!

01.06.2025 19:07 👍 0 🔁 0 💬 0 📌 0

🤔 or maybe it's time to try RL on cryptocurrencies.

25.05.2025 16:28 👍 1 🔁 0 💬 1 📌 0

I think Cs:go is not too different from cs2. So I don't see the problem here. I reviewed also some paper with it a few days ago. I think it is still an interesting 3D environment with many problems combined. Is there actually some API for RL with cs2 like psyc2 for StarCraft2?

22.05.2025 01:06 👍 0 🔁 0 💬 1 📌 0

What is the composition of your classes like? In our programs, the representation of society already ends in the technical courses. For example, we started a new course "AI Engineering". Result: 25 % women, although we really tried to adapt the marketing to attract more women.

22.04.2025 11:39 👍 0 🔁 0 💬 0 📌 0

Das heißt dann wohl, dass YouTube die bessere KI hat. ;)

18.04.2025 01:54 👍 1 🔁 0 💬 1 📌 0

Cool paper. Which author are you? I saw some earlier paper from this research group, which was interesting.

18.04.2025 01:51 👍 0 🔁 0 💬 2 📌 0

Das ist ja übel. Bei YouTube gibt's kein Limit, oder? Habe da sicher 2000 h oder so.

06.04.2025 01:17 👍 1 🔁 0 💬 1 📌 0

Is there any paper feedback before 9th May?

01.04.2025 01:59 👍 0 🔁 0 💬 0 📌 0

Just don't get famous and you can handle it. ;)

01.04.2025 01:55 👍 0 🔁 0 💬 0 📌 0

The hype will pass. I am happy how people can express now their ideas. Endless funny memes. Studio Ghibli got also some free marketing here. I am curious if Google will accomplish to reach the broad mass with their very good models as well. Gemini was faster but not so popular with this feature.

01.04.2025 01:53 👍 2 🔁 0 💬 0 📌 0

Very interesting! Addresses directly my research. I will definitely read it. Did you also experiment with MARL for MAPF?

31.03.2025 01:20 👍 2 🔁 0 💬 1 📌 0

Ok, thanks. I will definitely join this discord.

23.03.2025 02:58 👍 2 🔁 0 💬 0 📌 0

Oh no, totally missed this competition. How can I avoid to miss this? Usually I checked AIcrowd. Any further MARL challenges in the future?

23.03.2025 02:47 👍 2 🔁 0 💬 1 📌 0