Mohammad Ghavamzadeh
5 papers in the PaperMetrix corpus
Papers by this author
-
Graphical Model Sketch
2016 · arXiv (Cornell University)
Structured high-cardinality data arises in many domains, and poses a major challenge for both modeling and inference. Graphical models are a popular approach to modeling structured data but they are unsuitable for high-cardinality variables. The …
-
Control-Aware Representations for Model-based Reinforcement Learning
2020 · arXiv (Cornell University)
A major challenge in modern reinforcement learning (RL) is efficient control of dynamical systems from high-dimensional sensory observations. Learning controllable embedding (LCE) is a promising approach that addresses this challenge by embedding the observations into …
-
Variance-Reduced Off-Policy Memory-Efficient Policy Search
2020 · arXiv (Cornell University)
Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficiency, and have issues with …
-
Soft-Robust Algorithms for Handling Model Misspecification.
2020 · arXiv (Cornell University)
In reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the percentile criterion, which minimizes the probability of a catastrophic failure. Unfortunately, such policies are typically overly conservative …
-
Soft-Robust Algorithms for Batch Reinforcement Learning
2020 · arXiv (Cornell University)
In reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the percentile criterion, which minimizes the probability of a catastrophic failure. Unfortunately, such policies are typically overly conservative …