RL Theory Virtual Seminars

@rl-theory.bsky.social

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

Last seminars before the summer break: 04/29: Max Simchowitz (CMU) 05/06: Jeongyeol Kwon (Univ. of Widsconsin-Madison) 05/20: Sikata Sengupta & Marcel Hussing (Univ. of Pennsylvania) 05/27: Dhruv Rohatgi (MIT) 06/03: David Janz (Univ. of Oxford) 06/10: Nneka Okolo (MIT)

Bild

this breakthrough would not have been possible without the work of Asaf Cassel and Aviv Rosenberg, and the @rl-theory.bsky.social seminars where i have learned about their very clever trick for avoiding value-function truncations in policy optimization methods bsky.app/profile/rl-t...

RL Theory Virtual Seminars@rl-theory.bsky.social · 2y ago

Tomorrow at 6 PM UTC, Asaf Cassel will talk about "Warm-Up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes".