English
Related papers

Related papers: A Spectral Approach to Off-Policy Evaluation for P…

200 papers

Importance sampling-based estimators for off-policy evaluation (OPE) are valued for their simplicity, unbiasedness, and reliance on relatively few assumptions. However, the variance of these estimators is often high, especially when…

Machine Learning · Computer Science 2021-09-15 Simon P. Shen , Yecheng Jason Ma , Omer Gottesman , Finale Doshi-Velez

We consider a partially observable Markov decision problem (POMDP) that models a class of sequencing problems. Although POMDPs are typically intractable, our formulation admits tractable solution. Instead of maintaining a value function…

Artificial Intelligence · Computer Science 2013-01-14 Paat Rusmevichientong , Benjamin van Roy

Markov Decision Processes (MDPs) are stochastic optimization problems that model situations where a decision maker controls a system based on its state. Partially observed Markov decision processes (POMDPs) are generalizations of MDPs where…

Optimization and Control · Mathematics 2019-03-26 Victor Cohen , Axel Parmentier

We study planning problems where autonomous agents operate inside environments that are subject to uncertainties and not fully observable. Partially observable Markov decision processes (POMDPs) are a natural formal model to capture such…

Artificial Intelligence · Computer Science 2018-02-28 Steven Carr , Nils Jansen , Ralf Wimmer , Jie Fu , Ufuk Topcu

Off-policy learning in dynamic decision problems is essential for providing strong evidence that a new policy is better than the one in use. But how can we prove superiority without testing the new policy? To answer this question, we…

Machine Learning · Statistics 2015-02-12 Assaf Hallak , François Schnitzler , Timothy Mann , Shie Mannor

The agent learns to organize decision behavior to achieve a behavioral goal, such as reward maximization, and reinforcement learning is often used for this optimization. Learning an optimal behavioral strategy is difficult under the…

Machine Learning · Computer Science 2023-05-09 Kazuki Takahashi , Tomoki Fukai , Yutaka Sakai , Takashi Takekawa

In real-world recommender systems and search engines, optimizing ranking decisions to present a ranked list of relevant items is critical. Off-policy evaluation (OPE) for ranking policies is thus gaining a growing interest because it…

Machine Learning · Statistics 2022-02-04 Haruka Kiyohara , Yuta Saito , Tatsuya Matsuhiro , Yusuke Narita , Nobuyuki Shimizu , Yasuo Yamamoto

We introduce a class of partially observed Markov decision processes (POMDPs) with costs that can depend on both the value and (future) uncertainty associated with the initial state. These Initial-State Cost POMDPs (ISC-POMDPs) enable the…

Systems and Control · Electrical Eng. & Systems 2025-03-10 Timothy L. Molloy

The integration of physiological computing into mixed-initiative human-robot interaction systems offers valuable advantages in autonomous task allocation by incorporating real-time features as human state observations into the…

We study safe policy improvement (SPI) for partially observable Markov decision processes (POMDPs). SPI is an offline reinforcement learning (RL) problem that assumes access to (1) historical data about an environment, and (2) the so-called…

Artificial Intelligence · Computer Science 2023-01-13 Thiago D. Simão , Marnix Suilen , Nils Jansen

The problem of pure exploration in Markov decision processes has been cast as maximizing the entropy over the state distribution induced by the agent's policy, an objective that has been extensively studied. However, little attention has…

Machine Learning · Computer Science 2024-06-19 Riccardo Zamboni , Duilio Cirino , Marcello Restelli , Mirco Mutti

Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its…

Machine Learning · Computer Science 2020-08-12 Omer Gottesman , Joseph Futoma , Yao Liu , Sonali Parbhoo , Leo Anthony Celi , Emma Brunskill , Finale Doshi-Velez

We consider the problem of minimizing a certainty equivalent of the total or discounted cost over a finite and an infinite time horizon which is generated by a Partially Observable Markov Decision Process (POMDP). The certainty equivalent…

Probability · Mathematics 2021-07-21 Nicole Bäuerle , Ulrich Rieder

We propose a new approach to the problem of searching a space of policies for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP), given a model. Our approach is based on the following observation: Any…

Artificial Intelligence · Computer Science 2013-01-18 Andrew Y. Ng , Michael I. Jordan

Autonomous agents are limited in their ability to observe the world state. Partially observable Markov decision processes (POMDPs) formally model the problem of planning under world state uncertainty, but POMDPs with continuous actions and…

Robotics · Computer Science 2020-07-08 Dicong Qiu , Yibiao Zhao , Chris L. Baker

We consider the off-policy estimation problem of estimating the expected reward of a target policy using samples collected by a different behavior policy. Importance sampling (IS) has been a key technique to derive (nearly) unbiased…

Machine Learning · Computer Science 2018-10-31 Qiang Liu , Lihong Li , Ziyang Tang , Dengyong Zhou

The principal contribution of this paper is a conceptual framework for off-policy reinforcement learning, based on conditional expectations of importance sampling ratios. This framework yields new perspectives and understanding of existing…

Machine Learning · Computer Science 2020-07-31 Mark Rowland , Anna Harutyunyan , Hado van Hasselt , Diana Borsa , Tom Schaul , Rémi Munos , Will Dabney

We present a technique for speeding up the convergence of value iteration for partially observable Markov decisions processes (POMDPs). The underlying idea is similar to that behind modified policy iteration for fully observable Markov…

Artificial Intelligence · Computer Science 2013-01-30 Nevin Lianwen Zhang , Stephen S. Lee , Weihong Zhang

This paper is concerned with constructing a confidence interval for a target policy's value offline based on a pre-collected observational data in infinite horizon settings. Most of the existing works assume no unmeasured variables exist…

Machine Learning · Statistics 2022-11-07 Chengchun Shi , Jin Zhu , Ye Shen , Shikai Luo , Hongtu Zhu , Rui Song

This paper studies the synthesis of a joint control and active perception policy for a stochastic system modeled as a partially observable Markov decision process (POMDP), subject to temporal logic specifications. The POMDP actions…

Systems and Control · Electrical Eng. & Systems 2025-04-21 Chongyang Shi , Michael R. Dorothy , Jie Fu