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

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

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

LETTER doi:nature14236 Human-level control through deep reinforcement learning

Source URL: storage.googleapis.com

• Artificial intelligence
• Machine learning
• Computational neuroscience
• Applied mathematics
• Cybernetics
• Q-learning
• Artificial neural networks
• Reinforcement learning
• Convolutional neural network
• DQN
• Markov decision process
• Supervised learning

Microsoft PowerPoint - SEAri_TS_methods.pptx

Source URL: seari.mit.edu

• Epoch
• Engineering
• Statistical process control
• VisLab
• Chronology of the universe
• Science and technology
• Academia

AtomChase: Directed Search Towards Atomicity Violations Mahdi Eslamimehr, Mohsen Lesani This paper was presented at and awarded

Source URL: www.vpri.org

• Transaction processing
• Computing
• Data management
• Data
• Concurrency control
• Computer architecture
• Databases
• Atomicity
• Linearizability
• ARM architecture
• Process philosophy

Ownership, Experience and Defects: A fine-grained study of Authorship Foyzur Rahman and Premkumar Devanbu Department of Computer Science University of California, Davis, USA

Source URL: macbeth.cs.ucdavis.edu

• Software
• Computing
• Source code
• Software development process
• Version control systems
• Procedural programming languages
• Technical communication
• Version control
• Software quality
• Software bug
• Open-source software
• Source lines of code

CASE STUDY FAST GROWING RETAILER GAINS APPLICATION RELEASE EFFICIENCY AND CONTROL WITH SERENA DEPLOYMENT AUTOMATION SOLUTION

Source URL: www.serena.com

• Software
• Software release
• Computing
• Red Hat
• Application release automation
• Application software
• Software deployment
• Serena Software
• Release management
• Gordmans
• JBoss
• Business process automation

The CDCEtiologic Agent Import Permit Facility Inspection Process: David S. Bressler, MS, CBSP International Laboratory Branch Centers for Disease Control and Prevention

Source URL: absaconference.org