Strategy iteration is strongly polynomial for 2-player turn-based stochastic games with a constant discount factor Thomas Dueholm Hansen1,2 Peter Bro Miltersen1 Uri Zwick2 1

Source URL: cs.au.dk

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

The complexity of solving reachability games using value and strategy iteration ∗ Kristoffer Arnsfelt Hansen, Rasmus Ibsen-Jensen, and Peter Bro Miltersen Aarhus University {arnsfelt,rij,pbmiltersen}@cs.au.dk

Source URL: www.cs.au.dk

- Classification-based Policy Iteration with a Critic 1 1

Source URL: victorgabillon.nfshost.com

• Belief revision
• Reinforcement learning
• Dots per inch
• Mathematical optimization
• Rollout
• Artificial intelligence
• Applied mathematics
• Learning

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

CADGen Code Generator for Semi-Algebraic Iteration Sets Editionfor CADGen versionOctoberArmin Gr¨

Source URL: www.infosun.fim.uni-passau.de

Exercises in functional iteration: the function f(x) = ln(2-exp(-x)) A selfstudy using formal powerseries and operator-matrices Gottfried Helmsupdate

Source URL: go.helms-net.de

Rollout Allocation Strategies for Classification-based Policy Iteration Victor Gabillon Alessandro Lazaric

Source URL: victorgabillon.nfshost.com

• Mathematics
• Mathematical analysis
• Artificial intelligence
• Backgammon
• Rollout
• Markov decision process
• Multi-armed bandit
• Reinforcement learning
• Inverted pendulum
• Pendulum
• Prime-counting function
• Valuation

Hyperbolic Interpolation and Iteration towards a Zero File: 9Sep09 Version dated September 16, 2009 6:48 am

Source URL: http.cs.berkeley.edu