Positions

Research Areas research areas

Overview

  • Personal page: http://cs.unh.edu/~mpetrik

    • Selected Publications

    Academic Article

    Year Title
    2018 Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity.  Journal of Artificial Intelligence Research.  63:461-494. 2018
    2015 Tight Approximations of Dynamic Risk Measures.  Mathematics of Operations Research.  40:655-682. 2015
    2014 Social media and customer behavior analytics for personalized customer engagements.  IBM Journal of Research and Development.  58:7:1-7:12. 2014
    2014 Efficient and accurate methods for updating generalized linear models with multiple feature additions.  Journal of Machine Learning Research.  15:2607-2627. 2014
    2011 Robust approximate bilinear programming for value function approximation.  Journal of Machine Learning Research.  12:3027-3063. 2011
    2009 Hybrid least-squares algorithms for approximate policy evaluation.  Machine Learning.  76:243-256. 2009
    2009 A bilinear programming approach for multiagent planning.  Journal of Artificial Intelligence Research.  35:235-274. 2009
    2006 Learning parallel portfolios of algorithms.  Annals of Mathematics and Artificial Intelligence.  48:85-106. 2006
    2005 Learning parallel portfolios of algorithms 2005

    Conference Paper

    Year Title
    2019 Fast Feature Selection for Linear Value Function Approximation 2019
    2019 Inverse Reinforcement Learning of Interaction Dynamics from Demonstrations.  Proceedings - IEEE International Conference on Robotics and Automation. 2267-2274. 2019
    2019 Real-Time Planning as Decision-Making under Uncertainty.  THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE. 2338-2345. 2019
    2018 Low-rank Feature Selection for Reinforcement Learning 2018
    2018 Fast Bellman Updates for Robust MDPs.  INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 80. 2018
    2017 A Practical Method for Solving Contextual Bandit Problems Using Decision Trees.  Uncertainty in Artificial Intelligence (UAI). 2017
    2017 Robust Partially-Compressed Least-Squares Robust Partially-Compressed Least-Squares.  AAAI Conference on Artificial Intelligence. 2017
    2017 Value Directed Exploration in Multi-Armed Bandits with Structured Priors.  Uncertainty in Artificial Intelligence (UAI). 1-16. 2017
    2017 Value Directed Exploration in Multi-Armed Bandits with Structured Priors..  UAI. 2017
    2016 Building an Interpretable Recommender via Loss-Preserving Transformation.  CML Workshop on Human Interpretability in Machine Learning. 2016
    2016 Interpretable Policies for Dynamic Product Recommendations.  Uncertainty in Artificial Intelligence (UAI). 2016
    2016 Safe Policy Improvement by Minimizing Robust Baseline Regret.  Advances in Neural Information Processing Systems. 1-25. 2016
    2016 Safe Policy Improvement by Minimizing Robust Baseline Regret.  Advances in Neural Information Processing Systems. 2016
    2015 Optimal Threshold Control for Energy Arbitrage with Degradable Battery Storage.  Uncertainty in Artificial Intelligence (UAI). 692-701. 2015
    2014 RAAM : The benefits of robustness in approximating aggregated MDPs in reinforcement learning.  Neural Information Processing Systems (NIPS). 2014
    2013 Agile logistics simulation and optimization for managing disaster responses..  Winter Simulation Conference. 3340-3351. 2013
    2013 Solution methods for constrained Markov decision process with continuous probability modulation.  Uncertainty in Artificial Intelligence (UAI). 2013
    2012 An approximate solution method for large risk-averse Markov decision processes.  Uncertainty in Artificial Intelligence (UAI). 2012
    2012 Approximate dynamic programming by minimizing distributionally robust bounds.  International Conference of Machine Learning. 2012
    2012 Optimizing the end-to-end value chain through demand shaping and advanced customer analytics.  Symposium on Process Systems Engineering. 15-19. 2012
    2011 Linear dynamic programs for resource management.  Conference on Artificial Intelligence (AAAI). 2011
    2010 Feature selection using regularization in approximate linear programs for Markov decision processes.  International Conference on Machine Learning. 2010
    2009 Constraint relaxation in approximate linear programs.  International Conference on Machine Learning. 809-816. 2009
    2009 Robust value function approximation using bilinear programming.  Advances in Neural Information Processing Systems (NIPS). 2009
    2008 A successive approximation algorithm for coordination problems.  ISAIM. 2008
    2008 An analysis of linear models, linear value-function approximation, and feature selection for reinforcement learning.  Proceedings of the 25th international conference on Machine learning - ICML '08. 752-759. 2008
    2008 Biasing approximate dynamic programming with a lower discount factor.  Advances in Neural Information Processing Systems (NIPS). 2008
    2008 Interaction structure and dimensionality in decentralized problem solving.  Conference on Artificial Intelligence (AAAI). 1440-1441. 2008
    2008 Learning heuristic functions through approximate linear programming.  International Conference on Automated Planning and Scheduling (ICAPS). 2008
    2007 An analysis of Laplacian methods for value function approximation in MDPs.  International Joint Conference on Artificial Intelligence. 2574-2579. 2007
    2007 Anytime coordination using separable bilinear programs.  Conference on Artificial Intelligence. 750-755. 2007
    2007 Average-reward decentralized Markov decision processes.  International Joint Conference on Artificial Intelligence. 1997-2002. 2007
    Computing Robust Strategies for Managing Invasive Plants
    Policy Conditioned Uncertainty Sets for Robust Markov Decision Processes

    Teaching Activities

  • Advanced Machine Learning Taught course
  • Doctoral Research Taught course
  • Doctoral Research Taught course
  • Machine Learning Taught course
  • Mathematical Optimization Taught course
  • Mathematical Optimization Taught course
  • Doctoral Research Taught course 2024
  • Reinforcement Learning Taught course 2024
  • Doctoral Research Taught course 2023
  • Doctoral Research Taught course 2022
  • Doctoral Research Taught course 2022
  • Machine Learning Taught course 2022
  • Student Research Experience Taught course 2022
  • Advanced Machine Learning Taught course 2021
  • Doctoral Research Taught course 2021
  • Top/Reinforcemnt Machine Learn Taught course 2021
  • Advanced Machine Learning Taught course 2021
  • Advanced Machine Learning Taught course 2021
  • Doctoral Research Taught course 2021
  • Independent Study Taught course 2021
  • Machine Learning Taught course 2021
  • Machine Learning Taught course 2021
  • Mathematical Optimization Taught course 2021
  • Mathematical Optimization Taught course 2021
  • Doctoral Research Taught course 2020
  • Doctoral Research Taught course 2020
  • Machine Learning Taught course 2020
  • Mathematical Optimization Taught course 2020
  • Advanced Machine Learning Taught course 2019
  • Doctoral Research Taught course 2019
  • Independent Study Taught course 2019
  • Doctoral Research Taught course 2019
  • Machine Learning Taught course 2019
  • Mathematical Optimization Taught course 2019
  • Mathematical Optimization Taught course 2019
  • Mathematical Optimization Taught course 2019
  • Doctoral Research Taught course 2018
  • Topics/Machine Learning Taught course 2018
  • Independent Study Taught course 2018
  • Doctoral Research Taught course 2018
  • Independent Study Taught course 2018
  • Rsrch Exp/Computer Science Taught course 2018
  • Top/Machine Learning Taught course 2018
  • Independent Study/Honors Taught course 2017
  • Topics/Machine Learning Taught course 2017
  • Independent Study Taught course 2017
  • Top/Intro to Machine Learning Taught course 2017
  • Topics/Machine Learning Taught course 2016

    • Full Name

  • Marek Petrik