J. Fluid Mech), vol. 789, pp. 726–749. doi:jfmc Cambridge University Press 2016

Source URL: www.mattiagazzola.com

• Fisheries
• Fluid dynamics
• Mathematical analysis
• Dipole
• Electromagnetism
• Potential theory
• Reinforcement learning
• Swarm behaviour
• Shoaling and schooling
• Vorticity
• Q-learning
• Markov decision process

Decision-theoretic Clustering of Strategies

Source URL: poker.cs.ualberta.ca

• Computational statistics
• Statistics
• Mathematics
• K-means clustering
• Hierarchical clustering
• Cluster analysis
• Image segmentation
• K-means++
• Greedy algorithm
• K-medians clustering
• Data stream clustering
• Determining the number of clusters in a data set

Large-Scale Optimistic Adaptive Submodularity Victor Gabillon Branislav Kveton Zheng Wen

Source URL: victorgabillon.nfshost.com

• Mathematical analysis
• Mathematics
• Smooth functions
• Submodular set function
• Symbol
• Distribution
• Markov decision process
• operator
• Universal property

Guest Commentary Gastkommentar Active participation

Source URL: spotfire.tibco.com

• Business intelligence
• Economy
• Data analysis
• Information technology
• Analytics
• Predictive analytics
• Social BI
• Data mining
• Business process management
• Collaborative decision-making software
• Agile Business Intelligence

Finite-Sample Analysis in Reinforcement Learning Mohammad Ghavamzadeh INRIA Lille – Nord Europe, Team SequeL Outline

Source URL: mistis.inrialpes.fr

• Mathematics
• Dynamic programming
• Mathematical analysis
• Stochastic control
• Discrete mathematics
• Algebra
• Distribution
• Number theory
• Markov decision process
• Prime-counting function
• Mathematical optimization
• Projection-valued measure

Optimism in Sequential Decision-Making under Uncertainty Peter Bartlett Department of Statistics and Division of Computer Science UC Berkeley

Source URL: www.stat.berkeley.edu

• Mathematical analysis
• Dynamic programming
• Markov processes
• Stochastic control
• Statistical inference
• Analysis
• Operations research
• Markov decision process
• Regret
• Distribution
• S0
• Mathematical optimization

CSStat 260, Fall 2014: Learning in Sequential Decision Problems Lectures: Evans 334. Tuesday/Thursday 2:00-3:30. Instructor: Peter Bartlett http://www.stat.berkeley.edu/∼bartlett

Source URL: www.stat.berkeley.edu

• Mathematical optimization
• Operations research
• Mathematical analysis
• Numerical analysis
• Convex optimization
• Stochastic optimization
• Multi-armed bandit
• Game theory
• Linear programming
• AMPL

Stat 260/CSLearning in Sequential Decision Problems. Peter Bartlett 1. Recall: MDPs. 2. Value iteration. 3. Policy iteration.

Source URL: www.stat.berkeley.edu

• Markov processes
• Mathematics
• Probability theory
• Mathematical analysis
• Dynamic programming
• Markov decision process
• Stochastic control
• Markov chain
• Mathematical optimization
• Distribution

JMLR: Workshop and Conference Proceedings vol 40:1–14, 2015 Minimax Fixed-Design Linear Regression Peter L. Bartlett BARTLETT @ CS . BERKELEY. EDU

Source URL: jmlr.org

• Mathematics
• Estimation theory
• Regression analysis
• Statistics
• Decision theory
• Game theory
• Minimax
• Linear regression
• Regret
• Statistical theory

International Journal of Innovation, Management and Technology CONTENTS Volume 7, Number 1, February 2016 Disagreement Constrained Action Selection in Participatory Portfolio Decision Analysis ...........................

Source URL: www.ijimt.org