paper-with-me

Papers

Future-Dependent Value-Based Off-Policy Evaluation in POMDPs

2022-07-26 · NeurIPS 2023 11 · Masatoshi Uehara, Haruka Kiyohara, Andrew Bennett, Victor Chernozhukov, Nan Jiang, Nathan Kallus, Chengchun Shi, Wen Sun

We study off-policy evaluation (OPE) for partially observable MDPs (POMDPs) with general function approximation. Existing methods such as sequential importance sampling estimators and fitted-Q evaluation suffer from the curse of horizon in POMDPs. To circumvent this problem, we develop a novel model-free OPE method by introducing future-dependent value functions that take future proxies as inputs. Future-dependent value functions play similar roles as classical value functions in fully-observable MDPs. We derive a new Bellman equation for future-dependent value functions as conditional moment equations that use history proxies as instrumental variables. We further propose a minimax learning method to learn future-dependent value functions using the new Bellman equation. We obtain the PAC result, which implies our OPE estimator is consistent as long as futures and histories contain sufficient information about latent states, and the Bellman completeness. Finally, we extend our methods to learning of dynamics and establish the connection between our approach and the well-known spectral learning methods in POMDPs.

📄 PDF Abstract BibTeX arXiv:2207.13081

Code (1)

aiueola/neurips2023-future-dependent-ope 공식 구현 pytorch

Tasks

Off-policy evaluation

Similar Papers 제목 키워드 기반

On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation

2024-02-22 · Yuheng Zhang, Nan Jiang

We study off-policy evaluation (OPE) in partially observable environments with complex observations, with the goal of developing estimators whose guarantee avoids exponential dependence on the horizon. While such estimat…

Off-policy evaluation

Off-Policy Evaluation for Episodic Partially Observable Markov Decision Processes under Non-Parametric Models

2022-09-21 · Rui Miao, Zhengling Qi, Xiaoke Zhang

We study the problem of off-policy evaluation (OPE) for episodic Partially Observable Markov Decision Processes (POMDPs) with continuous states. Motivated by the recently proposed proximal causal inference framework, we …

Causal InferenceOff-policy evaluation

ISC-POMDPs: Partially Observed Markov Decision Processes with Initial-State Dependent Costs

2025-03-06 · Timothy L. Molloy

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-…

Robot Navigation

Memoryless Policy Iteration for Episodic POMDPs

2025-12-11 · Roy van Zuijlen, Duarte Antunes arxiv

Memoryless and finite-memory policies offer a practical alternative for solving partially observable Markov decision processes (POMDPs), as they operate directly in the output space rather than in the high-dimensional be…

A Covering Framework for Offline POMDPs Learning using Belief Space Metric

2026-03-03 · Youheng Zhu, Yiping Lu arxiv

In off policy evaluation (OPE) for partially observable Markov decision processes (POMDPs), an agent must infer hidden states from past observations, which exacerbates both the curse of horizon and the curse of memory in…