Все публикации

1:07:56

RL Theory Seminar 2024: Audrey Huang (October 22)

0:56:49

RL Theory Seminar 2024: Zakaria Mhammedi (October 15)

1:00:58

Zeyu Jia - Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data

0:33:28

Quanquan Gu - Self-Play Preference Optimization for Language Model Alignment

0:34:35

Simon Du - When are Offline Multi-Agent Games Solvable?

1:09:39

Shipra Agrawal - Optimistic Q-learning for average reward and episodic RL

0:32:15

Sharan Vaswani - Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs

0:34:15

Niao He - Reinforcement Learning in Mean Field Games: the pitfalls and promises

0:27:57

Philip Amortila - Scalable Online Exploration via Coverability

0:27:18

Philip Amortila - Statistical and Algorithmic Reductions for RL From Rich Observations

0:49:31

Gergely Neu - Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently

0:58:08

Ki Hong - Computationally Efficient Alg for Infinite-Horizon Average Reward RL with Linear MDPs

0:34:51

Ishani Aniruddha Karmarkar - Truncated Variance Reduced Value Iteration

0:31:15

Kevin Jamieson - On the Instance-dependent Sample Complexity of Tabular RL

0:32:00

Dongruo Zhou - Uncertainty-Aware Reward-Free Exploration with General Function Approximation

0:47:58

Brendan O’Donoghue - Efficient exploration in deep RL via utility theory

1:00:29

RL theory seminar 2024: Uri Sherman (May 14)

0:58:07

RL theory seminar 2024: Gene Li (May 7)

0:59:38

RL theory seminar 2024: Sergey Samsonov (Apr 30)

1:01:42

RL theory seminar 2024: Hamish Flynn (Apr 23)

1:03:05

RL theory seminar 2024: Andrew Wagenmaker (Apr 16)

1:00:19

RL theory seminar 2024: Ayush Sekhari (Apr 9)

1:10:27

RL theory seminar 2024: Matthew Zurek (Apr 2)

1:24:32

RL theory seminar 2024: Roberto Cipollone (Mar 26)