MAB-learning

A Multi-armed bandits learning group lasting four weeks

Members

• Shunan Jiang ([email protected])
• Yufeng Zheng (Hector) ([email protected])
• Mo Liu ([email protected])
• Hannah Jiang ([email protected])

Textbook

Aleksandrs Slivkins (2019), "Introduction to Multi-Armed Bandits", Foundations and Trends® in Machine Learning: Vol. 12: No. 1-2, pp 1-286. http://dx.doi.org/10.1561/2200000068

References

• (UW) CSE 599, Spring 2019, Reinforcement Learning and Bandits

Location

Zoom: https://berkeley.zoom.us/j/97478740713

Schedule

• June 15 19:30 PST, Shunan Jiang, Stochastic Bandits
• June 17 19:30 PST, Yufeng Zheng, Lower Bounds
• June 19 19:30 PST, Mo Liu, Bayesian Bandits and Thompson Sampling
• June 22 19:30 PST, Shunan Jiang, Lipschitz Bandits
• June 24 19:30 PST, Yufeng Zheng, Full Feedback and Adversarial Costs
• June 26 19:30 PST, Hansheng Jiang, Adversarial Bandits
• June 29 19:30 PST, Mo Liu, Linear Costs and Semi-bandits
• July 1 19:30 PST, Guanghao Ye, Contextual Bandits
• July 3 19:30 PST, Yufeng Zheng, Bandits and Games
• July 6 19:30 PST, Mo Liu, Bandits with Knapsacks
• July 8 19:30 PST, Shunan Jiang, Bandits and Incentives

Comments

Please feel free to join us on Zoom. If you're willing to contribute or have any comments, send us an email.