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!
27.05.2025 07:12 β π 18 π 3 π¬ 1 π 1
There is a new RL theory seminar tomorrow ! Join us :)
17.03.2025 10:25 β π 5 π 3 π¬ 0 π 0
Hope to see many of you joining !
10.03.2025 09:14 β π 1 π 0 π¬ 0 π 0
We are back today for this great talk !
26.11.2024 12:44 β π 0 π 0 π¬ 0 π 0
This is the official account of EWRL18 - European Workshop on Reinforcement Learning
Official website: https://euro-workshop-on-reinforcement-learning.github.io/ewrl18/
doing a phd in RL/online learning on questions related to exploration and adaptivity
> https://antoine-moulin.github.io/
Statistics, machine learning, numerics, and simulation at EURECOM.
Group Leader in TΓΌbingen, Germany
Iβm π«π· and I work on RL and lifelong learning. Mostly posting on ML related topics.
β·οΈ ML Theorist carving equations and mountain trails | π΄ββοΈ Biker, Climber, Adventurer | π§ Reinforcement Learning: Always seeking higher peaks, steeper walls and better policies.
https://ualberta.ca/~szepesva
Virtual seminar series featuring the latest advances in theoretical reinforcement learning. Seminars (approximately) every Tuesday at 6pm UTC.
> https://sites.google.com/corp/view/rltheoryseminars
full-time ML theory nerd, part-time AI-non enthusiast
official Bluesky account (check usernameπ)
Bugs, feature requests, feedback: support@bsky.app