Florian Felten

ffelten.bsky.social

27 April 2025 17:57

Unless they don't do it for citations. Which seems healthy 😅

Mattie Fellows

mattieml.bsky.social

19 March 2025 12:13

PQN Blog 1/3: TD methods are the bread and butter of RL, yet can have convergence issues when used in practice. This has always annoyed me. Find out below why TD is so unstable and how can we understand this instability better using the TD Jacobian. @flair-ox.bsky.social @jfoerst.bsky.social

Antoine Moulin

antoine-mln.bsky.social

20 February 2025 19:56

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!!

Tanishq Mathew Abraham

iscienceluvr.bsky.social

19 February 2025 13:36

Are folks still here? 😅

Mathieu Reymond

mreymond.bsky.social

18 February 2025 14:53

Our algo, IPRO, converges to the Pareto front and comes with strong guarantees with respect to the approximation error. Congrats Willem, and really glad to have been part of this work!