Interested in ✨world models✨? I just open-sourced an implementation of the Dreamer 4 world model. It's in PyTorch and comes with a pretrained model + a neat little web interface that lets you interact with any of 30 DMControl tasks that I trained it on!
Link: github.com/nicklashanse...
A good benchmark measures progress on a specific problem. I don't think it's possible to capture all aspects or applications of RL in one benchmark, so we'd first need to agree on what problem we even want to solve and then build a benchmark that acts as a (hopefully good) proxy for that problem.
Sounds like we need to prioritize building better benchmarks
maybe afternoon? it gets pretty cold once the sun sets
maybe embarcadero or waterfront park? would love to join
Yes I'd love to chat! I'll DM you
I'm in San Diego for NeurIPS! (...I live here, but I'm also attending NeurIPS)
I will be speaking at the Embodied World Models workshop on Saturday 10.00-10.30am. Let me know if you are around and would like to chat, or if you just need a food recc 🫶
(pictured: la jolla)
🎉 New work: “Learning Massively Multitask World Models for Continuous Control”
We introduce MMBench: a 200-task RL benchmark, and Newt: a language-conditioned multitask world model trained with large-scale online RL.
www.nicklashansen.com/NewtWM/
Code, checkpoints, dataset etc. are open-source!
View of Honolulu
I am in Honolulu for ICCV 2025 and will be speaking at the Reliable and Interactable World Models workshop at 11.20am tomorrow!
Let me know if you're around and want to chat about RL, world models, or anything else :-)
The sim2real demo had some mixed success, hampered primarily by the lighting conditions of the outdoors.
At least it worked sometimes! Hindsight says that despite the weather, low-cost nature, only 1 hour of training, anything working is a miracle
talk by @ncklashansen.bsky.social at the world models workshop starting now!
That's a very valid question but unfortunately not something I'm in a position to answer as a mere PhD student :-)
View of Marina Bay in Singapore
I will be in Singapore 🇸🇬 this week for ICLR 2025! Let me know if you're around and want to chat about RL, world models, LLMs, or anything else :-)
I am presenting two papers on model-based RL and also speaking at the World Models @ ICLR workshop on Monday.
(Photo is from my last trip to Singapore)
Congrats Nathan! Looking forward to reading it!
Honored to have NVIDIA feature my work! I'm grateful for the support and excited about all the recent progress in AI x robotics ✨
I am at GTC 2025! DM me if you're here and would like to chat about world models, RL, or anything else :-)
Thanks so much Mei! It was great to chat
Awesome, thank you!
Visualization of domains for which TD-MPC2 has been applied, including locomotion, manipulation, dexterous hands, humanoids, autonomous racing.
I finally joined 🦋! Some of you may recognize me from other sites. Here's a quick intro for new connections:
👋 I work on RL, world models, and generalization in decision-making. I'm perhaps most well known for my work on "TD-MPC2: Scalable, Robust World Models for Continuous Control" www.tdmpc2.com
