Théo Vincent
banner
theo-vincent.bsky.social
Théo Vincent
@theo-vincent.bsky.social
PhD student at @dfki | @ias-tudarmstadt.bsky.social, working on RL 🤖 Previously master student at MVA @ENS_ParisSaclay | ENPC 🎓
If you could not attend, here is a recorded version of my talk: youtube.com/watch?v=RCA2... 📽️
Théo Vincent - Optimizing the Learning Trajectory of Reinforcement Learning Agents
YouTube video by Cohere
youtube.com
September 19, 2025 at 4:08 PM
Many thanks to Rahul Narava for the invitation!

More information here: cohere.com/events/Coher...
Cohere Labs - Théo Vincent, Ph.D. student
Cohere Labs -Théo Vincent - Optimizing the Learning Trajectory of Reinforcement Learning Agents
cohere.com
July 11, 2025 at 4:21 PM
It was amazing to work on this project with Tim Faust, Yogesh Tripathi, @jan-peters.bsky.social, and Carlo D'Eramo!

Thanks to the funding agencies @ias-tudarmstadt.bsky.social, @cs-tudarmstadt.bsky.social, @dfki.bsky.social, @hessianai.bsky.social, and @uni-wuerzburg.de🏦
June 9, 2025 at 2:56 PM
Reposted by Théo Vincent
Learn more at the workshop website: egoact.github.io/rss2025

Happy to be organizing this with @georgiachal.bsky.social, Yu Xiang, @danfei.bsky.social and @galasso.bsky.social!
Web home for EgoAct: 1st Workshop on Egocentric Perception and Action for Robot Learning @ RSS2025
egoact.github.io
April 6, 2025 at 9:24 PM
I guess it depends on how off-policy you want to be. If you want to tune the RB size, I think it is a good idea to start with a large one (as @bramgrooten.bsky.social says) and reduce it if the agent struggles to learn.
December 11, 2024 at 4:39 PM