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

Haha true, the last part was mentally the toughest!

Totally agree

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!

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

Completed my first quarter triathlon today!

🏊‍♂️1 km swimming
🏃‍♂️11 km running
🚴‍♂️50 km cycling

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

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.

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

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

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

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

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

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

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!

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

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

🚀 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!
🧑‍💻 Apply now! openml-labs.github.io/website/join...
❣️Please share❣️

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

Presenting at #BNAIC, the Belgium-Netherlands AI Conference

bnaic2024.sites.uu.nl