10.9k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- University of BonnDE1.5k papers
- University of OxfordGB1.5k papers
- Lawrence Berkeley National LaboratoryUS1.5k papers
- Michigan State UniversityUS1.5k papers
- Stony Brook UniversityUS1.5k papers
- University of WuppertalDE1.5k papers
- The Ohio State UniversityUS1.5k papers
- Centre National de la Recherche ScientifiqueFR1.5k papers
- Stockholm UniversitySE1.4k papers
- Johannes Gutenberg University MainzDE1.4k papers
- Uppsala UniversitySE1.4k papers
- University of ManchesterGB1.4k papers
14 papers · 2 filters
State of the Art Control of Atari Games Using Shallow Reinforcement Learning
Yitao Liang, Marlos C. Machado, Erik Talvitie +1
The recently introduced Deep Q-Networks (DQN) algorithm has gained attention as one of the first successful combinations of deep neural networks and reinforcement learning. Its pro…
Weak Convergence Properties of Constrained Emphatic Temporal-difference Learning with Constant and Slowly Diminishing Stepsize
Huizhen Yu
We consider the emphatic temporal-difference (TD) algorithm, ETD(), for learning the value functions of stationary policies in a discounted, finite state and action Markov decis…
Blending LSTMs into CNNs
Krzysztof J. Geras, Abdel-rahman Mohamed, Rich Caruana +6
We consider whether deep convolutional networks (CNNs) can represent decision functions with similar accuracy as recurrent networks such as LSTMs. First, we show that a deep CNN wi…
Regret Analysis of the Finite-Horizon Gittins Index Strategy for Multi-Armed Bandits
Tor Lattimore
I analyse the frequentist regret of the famous Gittins index strategy for multi-armed bandits with Gaussian noise and a finite horizon. Remarkably it turns out that this approach l…
Label Efficient Learning by Exploiting Multi-class Output Codes
Maria Florina Balcan, Travis Dick, Yishay Mansour
We present a new perspective on the popular multi-class algorithmic techniques of one-vs-all and error correcting output codes. Rather than studying the behavior of these technique…
The Pareto Regret Frontier for Bandits
Tor Lattimore
Given a multi-armed bandit problem it may be desirable to achieve a smaller-than-usual worst-case regret for some special actions. I show that the price for such unbalanced worst-c…
Optimally Confident UCB: Improved Regret for Finite-Armed Bandits
Tor Lattimore
I present the first algorithm for stochastic finite-armed bandits that simultaneously enjoys order-optimal problem-dependent regret and worst-case regret. Besides the theoretical r…
Combinatorial Cascading Bandits
Branislav Kveton, Zheng Wen, Azin Ashkan +1
We propose combinatorial cascading bandits, a class of partial monitoring problems where at each step a learning agent chooses a tuple of ground items subject to constraints and re…
Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control
Prashanth L. A., Cheng Jie, Michael Fu +2
Cumulative prospect theory (CPT) is known to model human decisions well, with substantial empirical evidence supporting this claim. CPT works by distorting probabilities and is mor…
On Convergence of Emphatic Temporal-Difference Learning
Huizhen Yu
We consider emphatic temporal-difference learning algorithms for policy evaluation in discounted Markov decision processes with finite spaces. Such algorithms were recently propose…
Global and Local Structure Preserving Sparse Subspace Learning: An Iterative Approach to Unsupervised Feature Selection
Nan Zhou, Yangyang Xu, Hong Cheng +2
As we aim at alleviating the curse of high-dimensionality, subspace learning is becoming more popular. Existing approaches use either information about global or local structure of…
Temporal-Difference Networks
Richard S. Sutton, Brian Tanner
We introduce a generalization of temporal-difference (TD) learning to networks of interrelated predictions. Rather than relating a single prediction to itself at a later time, as i…
An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learning
Richard S. Sutton, A. Rupam Mahmood, Martha White
In this paper we introduce the idea of improving the performance of parametric temporal-difference (TD) learning algorithms by selectively emphasizing or de-emphasizing their updat…
Cascading Bandits: Learning to Rank in the Cascade Model
Branislav Kveton, Csaba Szepesvari, Zheng Wen +1
A search engine usually outputs a list of web pages. The user examines this list, from the first web page to the last, and chooses the first attractive page. This model of user…