Florian Felten
@ffelten.bsky.social
Postdoc @ETH | Multi-Objective RL | Optimization | Automated Design
I like to write cool libraries.
I cycle and run when I'm not lazy.
https://ffelten.github.io/
I like to write cool libraries.
I cycle and run when I'm not lazy.
https://ffelten.github.io/
Thanks for being part of the jury, your seminal work on this, and sharing, Peter. Really happy to have MORL under the spotlights.
October 26, 2025 at 9:24 PM
Thanks for being part of the jury, your seminal work on this, and sharing, Peter. Really happy to have MORL under the spotlights.
Looks promising, I struggled getting the actual difference with Isaac or MJWarp from their doc though.
October 10, 2025 at 11:55 AM
Looks promising, I struggled getting the actual difference with Isaac or MJWarp from their doc though.
Docs: engibench.ethz.ch
Paper: arxiv.org/abs/2508.00831
EngiBench: github.com/IDEALLab/Eng...
EngiOpt: github.com/IDEALLab/Eng...
🤗: huggingface.co/collections/...
We'd love your feedback--especially if you work at the ML x Optimization x Engineering Design intersection!
Paper: arxiv.org/abs/2508.00831
EngiBench: github.com/IDEALLab/Eng...
EngiOpt: github.com/IDEALLab/Eng...
🤗: huggingface.co/collections/...
We'd love your feedback--especially if you work at the ML x Optimization x Engineering Design intersection!
August 14, 2025 at 11:19 AM
Docs: engibench.ethz.ch
Paper: arxiv.org/abs/2508.00831
EngiBench: github.com/IDEALLab/Eng...
EngiOpt: github.com/IDEALLab/Eng...
🤗: huggingface.co/collections/...
We'd love your feedback--especially if you work at the ML x Optimization x Engineering Design intersection!
Paper: arxiv.org/abs/2508.00831
EngiBench: github.com/IDEALLab/Eng...
EngiOpt: github.com/IDEALLab/Eng...
🤗: huggingface.co/collections/...
We'd love your feedback--especially if you work at the ML x Optimization x Engineering Design intersection!
Our experiments show these engineering problems often have highly sensitive, constrained design spaces -> hard for current ML methods to handle.
We believe EngiBench & EngiOpt lay strong foundations for AI-driven engineering design and offer new challenges for the ML community.
We believe EngiBench & EngiOpt lay strong foundations for AI-driven engineering design and offer new challenges for the ML community.
August 14, 2025 at 11:19 AM
Our experiments show these engineering problems often have highly sensitive, constrained design spaces -> hard for current ML methods to handle.
We believe EngiBench & EngiOpt lay strong foundations for AI-driven engineering design and offer new challenges for the ML community.
We believe EngiBench & EngiOpt lay strong foundations for AI-driven engineering design and offer new challenges for the ML community.
EngiOpt ships with ready-to-use methods:
• Surrogate models
• GANs
• Diffusion models
• Optimization algorithms
All compatible with EngiBench and benchmarked on the problems.
Think of CleanRL for ML for Engineering Design.
• Surrogate models
• GANs
• Diffusion models
• Optimization algorithms
All compatible with EngiBench and benchmarked on the problems.
Think of CleanRL for ML for Engineering Design.
August 14, 2025 at 11:19 AM
EngiOpt ships with ready-to-use methods:
• Surrogate models
• GANs
• Diffusion models
• Optimization algorithms
All compatible with EngiBench and benchmarked on the problems.
Think of CleanRL for ML for Engineering Design.
• Surrogate models
• GANs
• Diffusion models
• Optimization algorithms
All compatible with EngiBench and benchmarked on the problems.
Think of CleanRL for ML for Engineering Design.
EngiBench provides:
⚙️ Physics-based simulators
📊 Benchmark problems & datasets across aeronautics, photonics, heat transfer & more
🔁 A unified API—swap problems in just 2 lines of code
Think of a Gymnasium for Engineering Design.
⚙️ Physics-based simulators
📊 Benchmark problems & datasets across aeronautics, photonics, heat transfer & more
🔁 A unified API—swap problems in just 2 lines of code
Think of a Gymnasium for Engineering Design.
August 14, 2025 at 11:18 AM
EngiBench provides:
⚙️ Physics-based simulators
📊 Benchmark problems & datasets across aeronautics, photonics, heat transfer & more
🔁 A unified API—swap problems in just 2 lines of code
Think of a Gymnasium for Engineering Design.
⚙️ Physics-based simulators
📊 Benchmark problems & datasets across aeronautics, photonics, heat transfer & more
🔁 A unified API—swap problems in just 2 lines of code
Think of a Gymnasium for Engineering Design.
Whether it uses tokenization or not, from a user's perspective it still doesn't feel particularly "smart" when prompted this way. Users shouldn't need to understand the inner workings to judge its quality, just as you don't need to know how a combustion engine works to enjoy a race car.
August 8, 2025 at 2:25 PM
Whether it uses tokenization or not, from a user's perspective it still doesn't feel particularly "smart" when prompted this way. Users shouldn't need to understand the inner workings to judge its quality, just as you don't need to know how a combustion engine works to enjoy a race car.
Unless they don't do it for citations. Which seems healthy 😅
April 22, 2025 at 7:37 PM
Unless they don't do it for citations. Which seems healthy 😅
"Have the confidence to cut. Don't keep something that doesn't fit just because you're proud of it, or because it cost you a lot of effort."
March 18, 2025 at 2:29 PM
"Have the confidence to cut. Don't keep something that doesn't fit just because you're proud of it, or because it cost you a lot of effort."
"Try to finish what you start, though, even if it turns out to be more work than you expected. Finishing things is not just an exercise in tidiness or self-discipline. In many projects a lot of the best work happens in what was meant to be the final stage."
March 18, 2025 at 2:29 PM
"Try to finish what you start, though, even if it turns out to be more work than you expected. Finishing things is not just an exercise in tidiness or self-discipline. In many projects a lot of the best work happens in what was meant to be the final stage."
"In most cases the recipe for doing great work is simply: work hard on excitingly ambitious projects, and something good will come of it."
March 18, 2025 at 2:29 PM
"In most cases the recipe for doing great work is simply: work hard on excitingly ambitious projects, and something good will come of it."
Thanks for the insights. RL is hard, and there should be more "hands-on" articles like this out there.
March 10, 2025 at 9:26 AM
Thanks for the insights. RL is hard, and there should be more "hands-on" articles like this out there.
Reposted by Florian Felten
🤖 AI that adapts to real-world challenges!
Florian Felten’s award-winning research on Multi-Objective Reinforcement Learning (MORL) is revolutionising AI decision-making, enabling smarter, context-sensitive agents that navigate complex environments.
#AI #innovation
Florian Felten’s award-winning research on Multi-Objective Reinforcement Learning (MORL) is revolutionising AI decision-making, enabling smarter, context-sensitive agents that navigate complex environments.
#AI #innovation
February 26, 2025 at 7:40 PM
🤖 AI that adapts to real-world challenges!
Florian Felten’s award-winning research on Multi-Objective Reinforcement Learning (MORL) is revolutionising AI decision-making, enabling smarter, context-sensitive agents that navigate complex environments.
#AI #innovation
Florian Felten’s award-winning research on Multi-Objective Reinforcement Learning (MORL) is revolutionising AI decision-making, enabling smarter, context-sensitive agents that navigate complex environments.
#AI #innovation
Having the LLM directly into the IDE removes one additional step in most cases
January 8, 2025 at 1:17 PM
Having the LLM directly into the IDE removes one additional step in most cases
Can be very efficiently encoded with a good sauce tokenizer
January 4, 2025 at 6:01 AM
Can be very efficiently encoded with a good sauce tokenizer
Did you input the sauces?
January 3, 2025 at 7:48 PM
Did you input the sauces?
Reposted by Florian Felten
If we look at paper counts, MORL continues to grow rapidly (around 40% per year since 2017). RL is also growing but has levelled out over the last few years (it will be interesting to see if the "RL is back" sentiment I've seen recently is reflected in 2025's publications).
January 1, 2025 at 2:07 AM
If we look at paper counts, MORL continues to grow rapidly (around 40% per year since 2017). RL is also growing but has levelled out over the last few years (it will be interesting to see if the "RL is back" sentiment I've seen recently is reflected in 2025's publications).
What are the main growth factors in your opinion, and how can we continue?
January 1, 2025 at 4:13 AM
What are the main growth factors in your opinion, and how can we continue?
The Bitter lesson comes back all the time. For RL, it is about time we recognize how underutilized our hardware is. The JAX based RL stuffs opened the way, but there is much more work ahead on parallel RL algos.
December 21, 2024 at 11:12 AM
The Bitter lesson comes back all the time. For RL, it is about time we recognize how underutilized our hardware is. The JAX based RL stuffs opened the way, but there is much more work ahead on parallel RL algos.