Classification-based Policy Iteration with a Critic V. Gabillon1 , A. Lazaric1 , M. Ghavamzadeh1 & B. Scherrer2 1 2 INRIA Lille - Nord Europe, Team Sequel,

Source URL: victorgabillon.nfshost.com

• Dynamic programming
• Markov decision process
• Stochastic control
• Probability theory
• Probability
• Statistics

Stat 260/CSLearning in Sequential Decision Problems. Peter Bartlett 1. Markov decision processes and partially observable Markov decision processes. 2. Value functions, Q functions.

Source URL: www.stat.berkeley.edu

• Markov processes
• Dynamic programming
• Probability theory
• Stochastic control
• Mathematical analysis
• Probability
• Markov models
• Markov decision process
• Mathematical optimization
• Markov chain
• Bellman equation
• X0

arXiv:1402.6763v1 [math.OC] 27 FebLinear Programming for Large-Scale Markov Decision Problems Yasin Abbasi-Yadkori Queensland University of Technology

Source URL: arxiv.org

• Mathematics
• Mathematical analysis
• Dynamic programming
• Markov decision process
• Stochastic control
• Distribution
• Probability theory
• Jet bundle
• Table of stars with Bayer designations

Deterministic MDPs with Adversarial Rewards and Bandit Feedback Raman Arora TTIC 6045 S. Kenwood Ave. Chicago, IL 60637, USA

Source URL: dept.stat.lsa.umich.edu

• Markov models
• Markov processes
• Stochastic optimization
• Mathematical optimization
• Operations research
• Reinforcement learning
• Markov decision process
• Algorithm
• Multi-armed bandit
• Dynamic programming
• Shortest path problem
• PP

approximate-mdps-notes.dvi

Source URL: www.stat.berkeley.edu

• Operations research
• Numerical analysis
• Mathematical optimization
• Mathematical analysis
• Optimal control
• Dynamic programming
• Markov decision process
• Stochastic control

Formalizing and Enforcing Purpose Restrictions in Privacy Policies (Full Version) Michael Carl Tschantz Anupam Datta Jeannette M. Wing March 22, 2012

Source URL: www.andrew.cmu.edu

• Dynamic programming
• Markov processes
• Stochastic control
• Markov decision process
• Reinforcement learning
• Health Insurance Portability and Accountability Act
• Privacy
• Medical record
• Internet privacy
• Bellman equation
• Personally identifiable information
• Policy

Robust Optimization with Recovery: Application to Shortest Paths and Airline Scheduling Niklaus Eggenberg, Transport and Mobility Laboratory, EPFL Matteo Salani, Transport and Mobility Laboratory, EPFL Michel Bierlaire,

Source URL: www.strc.ch

• Operations research
• Mathematical optimization
• Mathematics
• Mathematical analysis
• Shortest path problem
• Robust optimization
• Linear programming
• Stochastic optimization
• SAMPL
• Global optimization
• Scenario optimization

Solving Chance-Constrained Optimization Problems with Stochastic Quadratic Inequalities Miguel A. Lejeune∗, F. Margot† Abstract We study a complex class of stochastic programming problems involving a joint chance con

Source URL: wpweb2.tepper.cmu.edu

Optimal management of a stochastically varying population when policy adjustment is costly Carl Boettigera,∗, Michael Bodec , James N. Sanchiricob , Jacob LaRivieree , Alan Hastingsb , Paul R. Armsworthd arXiv:

Source URL: arxiv.org

• Economy
• Business
• Operations research
• Mathematical optimization
• Fisheries management
• Economics
• Stochastic programming
• Net present value
• Dynamic programming

Gossip Learning with Linear Models on Fully Distributed Data∗ Róbert Ormándi, István Heged˝us, Márk Jelasity University of Szeged and Hungarian Academy of Sciences {ormandi,ihegedus,jelasity}@inf.u-szeged.hu

Source URL: www.inf.u-szeged.hu

• Statistics
• Machine learning
• Computer programming
• Distributed computing
• File sharing
• Artificial neural networks
• Computational statistics
• Peer-to-peer
• Expectationmaximization algorithm
• Perceptron
• Supervised learning
• Stochastic gradient descent