Antoine Moulin
doing a phd in RL/online learning on questions related to exploration and adaptivity
> antoine-moulin.github.io
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine MoulinVery excited to share our preprint: Self-Speculative Masked Diffusions We speed up sampling of masked diffusion models by ~2x by using speculative sampling and a hybrid non-causal / causal transformer arxiv.org/abs/2510.03929 w/ @vdebortoli.bsky.social, Jiaxin Shi, @arnauddoucet.bsky.social
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- last year's edition was so much fun I'm really looking forward to this one!! join us in San Diego :))
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- new preprint with the amazing @lviano.bsky.social and @neu-rips.bsky.social on offline imitation learning! learned a lot :) when the expert is hard to represent but the environment is simple, estimating a Q-value rather than the expert directly may be beneficial. lots of open questions left though!
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin
[Not loaded yet] - Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Tim is amazing! go apply 🤩
- Last seminar before we take a short break to prepare for the next season! You can send us paper recommendations via this form: forms.gle/Uak8LpVPynNM...
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- super happy about this preprint! we can *finally* perform efficient exploration and find near-optimal stationary policies in infinite-horizon linear MDPs, and even use it for imitation learning :) working with @neu-rips.bsky.social and @lviano.bsky.social on this was so much fun!!
- can Grok 3 prove a lower bound on the bayesian regret though? didn't think so... but Itai can! today at 6 PM UTC
- Reposted by Antoine Moulin[Not loaded yet]
- just realized 2025 is the year when the Adam paper gets a test of time award and maybe TRPO? what else?
- Reposted by Antoine Moulin[Not loaded yet]
- We’re back! Join us for the next talks 🤓
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Yesterday was my last day at Google DeepMind. Interning there when the first GDM Nobel prize, AlphaProof, the Gemini releases and more all happened and having such amazing/ambitious colleagues was quite humbling and really exciting. I look forward to 2025!
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Very curious about this one! Join us tomorrow 🤓
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Reposted by Antoine Moulin[Not loaded yet]
- Join us tomorrow to learn about a magic trick to avoid an annoying truncation in linear MDPs!
- The RL theory virtual seminars are also on 🦋 now! Follow @rl-theory.bsky.social to hear about recent advances in RL theory :)
- Reposted by Antoine Moulin[Not loaded yet]
