Videos from Workshops

Playlist: 25 videos

Mathematics of Online Decision Making

Videos from Workshops Talks

Remote video URL
0:55:8

What Are the Statistical Limits of Offline Reinforcement Learning With Function Approximation?

Sham Kakade (University of Washington & Microsoft Research)
https://simons.berkeley.edu/talks/lower-bounds-batch-reinforcement-learning
Mathematics of Online Decision Making
Visit talk page
Remote video URL
0:30:42

An Alternative Softmax Operator for Reinforcement Learning

Michael Littman (Brown University)
An Alternative Softmax Operator for Reinforcement Learning
Mathematics of Online Decision Making
Visit talk page
Remote video URL
0:34:40

On the Global Convergence and Approximation Benefits of Policy Gradient Methods

Daniel Russo (Columbia University)
https://simons.berkeley.edu/talks/global-convergence-and-approximation-benefits-policy-gradient-methods
Mathematics of Online Decision Making
Visit talk page
Remote video URL
0:28:34

Corruption Robust Exploration in Episodic Reinforcement Learning

Aleksandrs Slivkins (Microsoft Research NYC)
https://simons.berkeley.edu/talks/corruption-robust-exploration-episodic-reinforcement-learning
Mathematics of Online Decision Making
Visit talk page
Remote video URL
0:29:56

Representation Learning and Exploration in Reinforcement Learning

Akshay Krishnamurthy (Microsoft Research)
https://simons.berkeley.edu/talks/representation-learning-and-exploration-reinforcement-learning
Mathematics of Online Decision Making
Visit talk page
Remote video URL
0:28:0

Multiplayer Bandit Learning - From Competition to Cooperation

Simina Branzei (Purdue University)
https://simons.berkeley.edu/talks/multiplayer-bandit-learning-competition-cooperation
Mathematics of Online Decision Making
Visit talk page
Remote video URL
0:32:28

Multi-Player Multi-Armed Bandit: Can We Still Collaborate at Homes Without "Zoom"?

Yuanzhi Li (Carnegie Mellon University)
https://simons.berkeley.edu/talks/multi-player-multi-armed-bandit-can-we-still-collaborate-homes-without-zoom
Mathematics of Online Decision Making
Visit talk page
Remote video URL
0:31:38

Country-Scale Bandit Implementation for Targeted COVID-19 Testing

Hamsa Bastani (Wharton School of the University of Pennsylvania)
https://simons.berkeley.edu/talks/country-scale-bandit-implementation-targeted-covid-19-testing
Mathematics of Online Decision Making
Visit talk page
Remote video URL
0:40:53

Online Learning via Offline Greedy Algorithms: Applications in Market Design and Optimization

Negin Golrezaei (MIT)
https://simons.berkeley.edu/talks/online-learning-offline-greedy-algorithms-applications-market-design-and-optimization
Mathematics of Online Decision Making
Visit talk page
Remote video URL
0:35:41

Beating the Curse of Dimensionality in High-Dimensional Optimal Stopping

David Goldberg (Cornell ORIE)
https://simons.berkeley.edu/talks/beating-curse-dimensionality-high-dimensional-optimal-stopping
Mathematics of Online Decision Making
Visit talk page