Mei Han
@imeimei.bsky.social
Reposted by Mei Han
🎉 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!
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!
November 25, 2025 at 7:47 PM
🎉 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!
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!