Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Aleksandrs Slivkins

Aleksandrs Slivkins

Incentivizing Combinatorial Bandit Exploration



Xinyan Hu , Dung Daniel Ngo , Aleksandrs Slivkins , Zhiwei Steven Wu

* 9 pages of main text, 21 pages in total 
   Access Paper or Ask Questions

Sayer: Using Implicit Feedback to Optimize System Policies



Mathias Lécuyer , Sang Hoon Kim , Mihir Nanavati , Junchen Jiang , Siddhartha Sen , Amit Sharma , Aleksandrs Slivkins

Figure 1 for Sayer: Using Implicit Feedback to Optimize System Policies
Figure 2 for Sayer: Using Implicit Feedback to Optimize System Policies
Figure 3 for Sayer: Using Implicit Feedback to Optimize System Policies
Figure 4 for Sayer: Using Implicit Feedback to Optimize System Policies

   Access Paper or Ask Questions

Exploration and Incentives in Reinforcement Learning



Max Simchowitz , Aleksandrs Slivkins


   Access Paper or Ask Questions

Competing Bandits: The Perils of Exploration Under Competition



Guy Aridor , Yishay Mansour , Aleksandrs Slivkins , Zhiwei Steven Wu

Figure 1 for Competing Bandits: The Perils of Exploration Under Competition
Figure 2 for Competing Bandits: The Perils of Exploration Under Competition
Figure 3 for Competing Bandits: The Perils of Exploration Under Competition
Figure 4 for Competing Bandits: The Perils of Exploration Under Competition
* merged and extended version of arXiv:1702.08533 and arXiv:1902.05590 
   Access Paper or Ask Questions

Adaptive Discretization for Adversarial Bandits with Continuous Action Spaces



Chara Podimata , Aleksandrs Slivkins


   Access Paper or Ask Questions

Efficient Contextual Bandits with Continuous Actions



Maryam Majzoubi , Chicheng Zhang , Rajan Chari , Akshay Krishnamurthy , John Langford , Aleksandrs Slivkins

Figure 1 for Efficient Contextual Bandits with Continuous Actions
Figure 2 for Efficient Contextual Bandits with Continuous Actions
Figure 3 for Efficient Contextual Bandits with Continuous Actions
Figure 4 for Efficient Contextual Bandits with Continuous Actions

   Access Paper or Ask Questions

Constrained episodic reinforcement learning in concave-convex and knapsack settings



Kianté Brantley , Miroslav Dudik , Thodoris Lykouris , Sobhan Miryoosefi , Max Simchowitz , Aleksandrs Slivkins , Wen Sun

Figure 1 for Constrained episodic reinforcement learning in concave-convex and knapsack settings
Figure 2 for Constrained episodic reinforcement learning in concave-convex and knapsack settings

   Access Paper or Ask Questions

Greedy Algorithm almost Dominates in Smoothed Contextual Bandits



Manish Raghavan , Aleksandrs Slivkins , Jennifer Wortman Vaughan , Zhiwei Steven Wu

* Results in this paper, without any proofs, have been announced in an extended abstract (Raghavan et al., 2018a), and fleshed out in the technical report (Raghavan et al., 2018b [arXiv:1806.00543]). This manuscript covers a subset of results from Raghavan et al. (2018a,b), focusing on the greedy algorithm, and is streamlined accordingly 
   Access Paper or Ask Questions

Sample Complexity of Incentivized Exploration



Mark Sellke , Aleksandrs Slivkins


   Access Paper or Ask Questions

Advances in Bandits with Knapsacks



Karthik Abinav Sankararaman , Aleksandrs Slivkins


   Access Paper or Ask Questions
1
2
3
4
>>