paper-with-me

Papers

Off-Policy Interval Estimation with Lipschitz Value Iteration

2020-10-29 · NeurIPS 2020 12 · Ziyang Tang, Yihao Feng, Na Zhang, Jian Peng, Qiang Liu

Off-policy evaluation provides an essential tool for evaluating the effects of different policies or treatments using only observed data. When applied to high-stakes scenarios such as medical diagnosis or financial decision-making, it is crucial to provide provably correct upper and lower bounds of the expected reward, not just a classical single point estimate, to the end-users, as executing a poor policy can be very costly. In this work, we propose a provably correct method for obtaining interval bounds for off-policy evaluation in a general continuous setting. The idea is to search for the maximum and minimum values of the expected reward among all the Lipschitz Q-functions that are consistent with the observations, which amounts to solving a constrained optimization problem on a Lipschitz function space. We go on to introduce a Lipschitz value iteration method to monotonically tighten the interval, which is simple yet efficient and provably convergent. We demonstrate the practical efficiency of our method on a range of benchmarks.

📄 PDF Abstract BibTeX arXiv:2010.15392

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingMedical DiagnosisOff-policy evaluation

Similar Papers 제목 키워드 기반

A Contracting Dynamical System Perspective toward Interval Markov Decision Processes

2023-09-17 · Saber Jafarpour, Samuel Coogan

Interval Markov decision processes are a class of Markov models where the transition probabilities between the states belong to intervals. In this paper, we study the problem of efficient estimation of the optimal polici…

Neural Policy Iteration for Stochastic Optimal Control: A Physics-Informed Approach

2025-08-03 · Yeongjong Kim, Yeoneung Kim, Minseok Kim, Namkyeong Cho arxiv

We propose a physics-informed neural network policy iteration (PINN-PI) framework for solving stochastic optimal control problems governed by second-order Hamilton--Jacobi--Bellman (HJB) equations. At each iteration, a n…

Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration

2023-05-25 · Blaise Delattre, Quentin Barthélemy, Alexandre Araujo, Alexandre Allauzen

Since the control of the Lipschitz constant has a great impact on the training stability, generalization, and robustness of neural networks, the estimation of this value is nowadays a real scientific challenge. In this p…

Accountable Off-Policy Evaluation via a Kernelized Bellman Statistics

2020-01-01 · ICML 2020 1 · Yihao Feng, Tongzheng Ren, Ziyang Tang, Qiang Liu

Off-policy evaluation plays an important role in modern reinforcement learning. However, most of the existing off-policy evaluation only focus on the value estimation, without providing an accountable confidence interval…

Off-policy evaluation

Solving nonconvex Hamilton--Jacobi--Isaacs equations with PINN-based policy iteration

2025-07-21 · Hee Jun Yang, Minjung Gim, Yeoneung Kim arxiv

We propose a mesh-free policy iteration framework that combines classical dynamic programming with physics-informed neural networks (PINNs) to solve high-dimensional, nonconvex Hamilton--Jacobi--Isaacs (HJI) equations ar…

Multi-agent Reinforcement Learning