253 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- University of New HampshireUS40 papers
- University of California, BerkeleyUS27 papers
- Los Alamos National LaboratoryUS20 papers
- Goddard Space Flight CenterUS16 papers
- Thomas Jefferson National Accelerator FacilityUS16 papers
- University of Tennessee at KnoxvilleUS16 papers
- University of VirginiaUS13 papers
- Massachusetts Institute of TechnologyUS12 papers
- Argonne National LaboratoryUS11 papers
- Université Paris-SaclayFR11 papers
- Johns Hopkins University Applied Physics LaboratoryUS10 papers
- Lawrence Berkeley National LaboratoryUS10 papers
5 papers · 1 filter
Policy Gradient Bayesian Robust Optimization for Imitation Learning
Zaynah Javed, Daniel S. Brown, Satvik Sharma +5
The difficulty in specifying rewards for many real-world problems has led to an increased focus on learning rewards from human feedback, such as demonstrations. However, there are…
Robust Maximum Entropy Behavior Cloning
Mostafa Hussein, Brendan Crowe, Marek Petrik +1
Imitation learning (IL) algorithms use expert demonstrations to learn a specific task. Most of the existing approaches assume that all expert demonstrations are reliable and trustw…
Soft-Robust Algorithms for Batch Reinforcement Learning
Elita A. Lobo, Mohammad Ghavamzadeh, Marek Petrik
In reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the percentile criterion, which minimizes t…
Partial Policy Iteration for L1-Robust Markov Decision Processes
Chin Pang Ho, Marek Petrik, Wolfram Wiesemann
Robust Markov decision processes (MDPs) allow to compute reliable solutions for dynamic decision problems whose evolution is modeled by rewards and partially-known transition proba…
A Practical Method for Solving Contextual Bandit Problems Using Decision Trees
Adam N. Elmachtoub, Ryan McNellis, Sechan Oh +1
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…