Bram Grooten's Avatar

Bram Grooten

@bramgrooten

PhD student at the TU Eindhoven. Researching deep learning, RL, sparse neural networks, robotics.

2,047
Followers
69
Following
15
Posts
02.11.2023
Joined
Posts Following

Latest posts by Bram Grooten @bramgrooten

Baseball season starts tomorrow! Looking forward to being out on the field all day ⚾

15.03.2025 21:49 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Haha true, the last part was mentally the toughest!

04.02.2025 13:44 πŸ‘ 2 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Totally agree

04.02.2025 09:19 πŸ‘ 3 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Haha thanks, no worries. It was kind of spontaneous. I started the day with 30km cycling, then 1km swimming. Then I realized I could make this into a quarter triathlon, so ran 11km and added an extra 20km on the bike!

04.02.2025 07:10 πŸ‘ 3 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

The swimming part was by far the hardest for me. And about the cycling: I was on my electric bike, so let's call it an electric quarter triathlon

03.02.2025 20:42 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Completed my first quarter triathlon today!

πŸŠβ€β™‚οΈ1 km swimming
πŸƒβ€β™‚οΈ11 km running
πŸš΄β€β™‚οΈ50 km cycling

Took a long weekend, in the transition from Sony AI intern back to PhD student :)

03.02.2025 20:39 πŸ‘ 8 πŸ” 0 πŸ’¬ 2 πŸ“Œ 0
Post image

I am teaching a class on #FoundationalModels for #robotics and Scaling #DeepRL algorithms. This class expands on last year's class and my generalist robotics policies tutorial and code. I plan to share the lectures and code assignments. Starting with the first lectures below.

19.01.2025 19:14 πŸ‘ 21 πŸ” 6 πŸ’¬ 1 πŸ“Œ 0

I'm also curious to hear @shibhansh.bsky.social's opinion. On what timescale did loss of plasticity usually occur in your RL experiments? :)

10.01.2025 16:54 πŸ‘ 1 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

Thanks! That's interesting. Would indeed make sense that CL issues happen more often in more complex environments that require longer training.

10.01.2025 16:51 πŸ‘ 0 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

How long does an RL agent usually need to be trained before you notice CL problems, would you say?

10.01.2025 06:48 πŸ‘ 0 πŸ” 0 πŸ’¬ 2 πŸ“Œ 0

Great speech. I think many AI researchers are also intrinsically motivated by these Real Reasons.

01.01.2025 09:35 πŸ‘ 1 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0
Post image

After six years of listening to it, the family turned it into a shirt

31.12.2024 19:34 πŸ‘ 127 πŸ” 2 πŸ’¬ 5 πŸ“Œ 0

What I often see is that people just take buffer size = time steps. Up to a max of about 2M

11.12.2024 14:36 πŸ‘ 1 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

If you're at NeurIPS, RLC is hosting an RL event from 8 till late at The Pearl on Dec. 11th. Join us, meet all the RL researchers, and spread the word!

10.12.2024 21:55 πŸ‘ 63 πŸ” 18 πŸ’¬ 2 πŸ“Œ 4
Post image Post image Post image Post image

For those at #NeurIPS: I really enjoyed the Capilano Suspension Bridge after sunset yesterday. Would recommend!

10.12.2024 14:27 πŸ‘ 9 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

I've been working on this game with #SonyAI for the past few months. Great to see how popular it actually is!

07.12.2024 19:52 πŸ‘ 3 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0
Post image

πŸš€ Ready to push the boundaries of #AI & #ML? We're hiring 7(!) brilliant PhDs, PostDocs, and Engineers to work on cutting-edge #LLMs #AutoML #ContinualLearning
@TUeindhoven

🌟 Think big and shape the future of AI!
πŸ§‘β€πŸ’» Apply now! openml-labs.github.io/website/join...
❣️Please share❣️

06.12.2024 16:25 πŸ‘ 14 πŸ” 7 πŸ’¬ 0 πŸ“Œ 0
Preview
Boosting Robustness in Preference-Based Reinforcement Learning with Dynamic Sparsity For autonomous agents to successfully integrate into human-centered environments, agents should be able to learn from and adapt to humans in their native settings. Preference-based reinforcement learn...

We worked on making PbRL more robust to noisy envs recently:
arxiv.org/abs/2406.06495

22.11.2024 09:13 πŸ‘ 2 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0
Post image

Presenting at #BNAIC, the Belgium-Netherlands AI Conference

bnaic2024.sites.uu.nl

19.11.2024 07:39 πŸ‘ 7 πŸ” 1 πŸ’¬ 0 πŸ“Œ 0