Approximate Dynamic Programming By Minimizing Distributionally Robust Bounds

May 21, 2012

Marek Petrik

May 21, 2012

Marek Petrik

* In Proceedings of International Conference on Machine Learning, 2012

**Click to Read Paper and Get Code**

Interpretable Reinforcement Learning with Ensemble Methods

Sep 19, 2018

Alexander Brown, Marek Petrik

Sep 19, 2018

Alexander Brown, Marek Petrik

**Click to Read Paper and Get Code**

A Bilinear Programming Approach for Multiagent Planning

Jan 15, 2014

Marek Petrik, Shlomo Zilberstein

Jan 15, 2014

Marek Petrik, Shlomo Zilberstein

* Journal Of Artificial Intelligence Research, Volume 35, pages 235-274, 2009

**Click to Read Paper and Get Code**

An Approximate Solution Method for Large Risk-Averse Markov Decision Processes

Oct 16, 2012

Marek Petrik, Dharmashankar Subramanian

Oct 16, 2012

Marek Petrik, Dharmashankar Subramanian

* Appears in Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence (UAI2012)

**Click to Read Paper and Get Code**

**Click to Read Paper and Get Code**

Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs

Feb 20, 2019

Marek Petrik, Reazul Hasan Russell

Feb 20, 2019

Marek Petrik, Reazul Hasan Russell

**Click to Read Paper and Get Code**

* 5 pages. Accepted at Infer to Control Workshop at Neural Information Processing Systems (NIPS) 2018

**Click to Read Paper and Get Code**

Safe Policy Improvement by Minimizing Robust Baseline Regret

Jul 13, 2016

Marek Petrik, Yinlam Chow, Mohammad Ghavamzadeh

Jul 13, 2016

Marek Petrik, Yinlam Chow, Mohammad Ghavamzadeh

**Click to Read Paper and Get Code**

Building an Interpretable Recommender via Loss-Preserving Transformation

Jun 19, 2016

Amit Dhurandhar, Sechan Oh, Marek Petrik

Jun 19, 2016

Amit Dhurandhar, Sechan Oh, Marek Petrik

* Presented at 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016), New York, NY

**Click to Read Paper and Get Code**

Solution Methods for Constrained Markov Decision Process with Continuous Probability Modulation

Sep 26, 2013

Marek Petrik, Dharmashankar Subramanian, Janusz Marecki

Sep 26, 2013

Marek Petrik, Dharmashankar Subramanian, Janusz Marecki

* Appears in Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI2013)

**Click to Read Paper and Get Code**

Robust Exploration with Tight Bayesian Plausibility Sets

Apr 17, 2019

Reazul H. Russel, Tianyi Gu, Marek Petrik

Optimism about the poorly understood states and actions is the main driving force of exploration for many provably-efficient reinforcement learning algorithms. We propose optimism in the face of sensible value functions (OFVF)- a novel data-driven Bayesian algorithm to constructing Plausibility sets for MDPs to explore robustly minimizing the worst case exploration cost. The method computes policies with tighter optimistic estimates for exploration by introducing two new ideas. First, it is based on Bayesian posterior distributions rather than distribution-free bounds. Second, OFVF does not construct plausibility sets as simple confidence intervals. Confidence intervals as plausibility sets are a sufficient but not a necessary condition. OFVF uses the structure of the value function to optimize the location and shape of the plausibility set to guarantee upper bounds directly without necessarily enforcing the requirement for the set to be a confidence interval. OFVF proceeds in an episodic manner, where the duration of the episode is fixed and known. Our algorithm is inherently Bayesian and can leverage prior information. Our theoretical analysis shows the robustness of OFVF, and the empirical results demonstrate its practical promise.
Apr 17, 2019

Reazul H. Russel, Tianyi Gu, Marek Petrik

**Click to Read Paper and Get Code**

Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes

May 20, 2010

Marek Petrik, Gavin Taylor, Ron Parr, Shlomo Zilberstein

May 20, 2010

Marek Petrik, Gavin Taylor, Ron Parr, Shlomo Zilberstein

* Technical report corresponding to the ICML2010 submission of the same name

**Click to Read Paper and Get Code**

A Practical Method for Solving Contextual Bandit Problems Using Decision Trees

Oct 19, 2018

Adam N. Elmachtoub, Ryan McNellis, Sechan Oh, Marek Petrik

Many efficient algorithms with strong theoretical guarantees have been proposed for the contextual multi-armed bandit problem. However, applying these algorithms in practice can be difficult because they require domain expertise to build appropriate features and to tune their parameters. We propose a new method for the contextual bandit problem that is simple, practical, and can be applied with little or no domain expertise. Our algorithm relies on decision trees to model the context-reward relationship. Decision trees are non-parametric, interpretable, and work well without hand-crafted features. To guide the exploration-exploitation trade-off, we use a bootstrapping approach which abstracts Thompson sampling to non-Bayesian settings. We also discuss several computational heuristics and demonstrate the performance of our method on several datasets.
Oct 19, 2018

Adam N. Elmachtoub, Ryan McNellis, Sechan Oh, Marek Petrik

* Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence (UAI 2017)

**Click to Read Paper and Get Code**

Value Directed Exploration in Multi-Armed Bandits with Structured Priors

May 17, 2017

Bence Cserna, Marek Petrik, Reazul Hasan Russel, Wheeler Ruml

May 17, 2017

Bence Cserna, Marek Petrik, Reazul Hasan Russel, Wheeler Ruml

**Click to Read Paper and Get Code**

Robust Partially-Compressed Least-Squares

Oct 16, 2015

Stephen Becker, Ban Kawas, Marek Petrik, Karthikeyan N. Ramamurthy

Oct 16, 2015

Stephen Becker, Ban Kawas, Marek Petrik, Karthikeyan N. Ramamurthy

**Click to Read Paper and Get Code**