English
Related papers

Related papers: Future-Dependent Value-Based Off-Policy Evaluation…

200 papers

The low rank MDP has emerged as an important model for studying representation learning and exploration in reinforcement learning. With a known representation, several model-free exploration strategies exist. In contrast, all algorithms for…

Machine Learning · Computer Science 2022-06-23 Aditya Modi , Jinglin Chen , Akshay Krishnamurthy , Nan Jiang , Alekh Agarwal

Finding optimal policies for Partially Observable Markov Decision Processes (POMDPs) is challenging due to their uncountable state spaces when transformed into fully observable Markov Decision Processes (MDPs) using belief states.…

Optimization and Control · Mathematics 2024-09-09 Yunus Emre Demirci , Ali Devran Kara , Serdar Yüksel

Off-policy evaluation (OPE) is to evaluate a target policy with data generated by other policies. Most previous OPE methods focus on precisely estimating the true performance of a policy. We observe that in many applications, (1) the end…

Machine Learning · Computer Science 2022-06-22 Yue Jin , Yue Zhang , Tao Qin , Xudong Zhang , Jian Yuan , Houqiang Li , Tie-Yan Liu

The standard problem setting in Dec-POMDPs is self-play, where the goal is to find a set of policies that play optimally together. Policies learned through self-play may adopt arbitrary conventions and implicitly rely on multi-step…

Artificial Intelligence · Computer Science 2021-08-19 Hengyuan Hu , Adam Lerer , Brandon Cui , David Wu , Luis Pineda , Noam Brown , Jakob Foerster

Partially Observable Markov Decision Processes (POMDPs) provide a robust framework for decision-making under uncertainty in applications such as autonomous driving and robotic exploration. Their extension, $\rho$POMDPs, introduces…

Artificial Intelligence · Computer Science 2025-02-05 Ron Benchetrit , Idan Lev-Yehudi , Andrey Zhitnikov , Vadim Indelman

Reinforcement learning (RL) algorithms still suffer from high sample complexity despite outstanding recent successes. The need for intensive interactions with the environment is especially observed in many widely popular policy gradient…

Machine Learning · Computer Science 2020-08-04 Samuele Tosatto , Joao Carvalho , Hany Abdulsamad , Jan Peters

We consider off-policy temporal-difference (TD) learning in discounted Markov decision processes, where the goal is to evaluate a policy in a model-free way by using observations of a state process generated without executing the policy. To…

Machine Learning · Computer Science 2018-11-27 Huizhen Yu , A. Rupam Mahmood , Richard S. Sutton

We consider the reinforcement learning problem for partially observed Markov decision processes (POMDPs) with large or even countably infinite state spaces, where the controller has access to only noisy observations of the underlying…

Machine Learning · Computer Science 2023-07-20 Semih Cayci , Niao He , R. Srikant

Markov decision processes (MDPs) with rewards are a widespread and well-studied model for systems that make both probabilistic and nondeterministic choices. A fundamental result about MDPs is that their minimal and maximal expected rewards…

Logic in Computer Science · Computer Science 2024-11-26 Kevin Batz , Benjamin Lucien Kaminski , Christoph Matheja , Tobias Winkler

In many real-world planning tasks, agents must tackle uncertainty about the environment's state and variability in the outcomes induced by stochastic dynamics and rewards. Motivated by recent progress in world model approaches, where latent…

Artificial Intelligence · Computer Science 2026-05-07 Larry Preuett , Qiuyi Zhang , Muhammad Aurangzeb Ahmad

Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) are known to be NEXP-Complete and intractable to solve. However, for problems such as cooperative navigation, obstacle avoidance, and formation control, basic…

Multiagent Systems · Computer Science 2025-06-05 Alex DeWeese , Guannan Qu

Uncertain partially observable Markov decision processes (uPOMDPs) allow the probabilistic transition and observation functions of standard POMDPs to belong to a so-called uncertainty set. Such uncertainty, referred to as epistemic…

Artificial Intelligence · Computer Science 2021-11-02 Murat Cubuktepe , Nils Jansen , Sebastian Junges , Ahmadreza Marandi , Marnix Suilen , Ufuk Topcu

Off-policy evaluation (OPE) methods allow us to compute the expected reward of a policy by using the logged data collected by a different policy. OPE is a viable alternative to running expensive online A/B tests: it can speed up the…

Machine Learning · Computer Science 2024-10-23 Matej Cief , Jacek Golebiowski , Philipp Schmidt , Ziawasch Abedjan , Artur Bekasov

This paper describes sufficient conditions for the existence of optimal policies for Partially Observable Markov Decision Processes (POMDPs) with Borel state, observation, and action sets and with the expected total costs. Action sets may…

Optimization and Control · Mathematics 2014-07-02 Eugene A. Feinberg , Pavlo O. Kasyanov , Michael Z. Zgurovsky

Many sequential decision problems involve optimizing one objective function while imposing constraints on other objectives. Constrained Partially Observable Markov Decision Processes (C-POMDP) model this case with transition uncertainty and…

We present the first finite-sample analysis of policy evaluation in robust average-reward Markov Decision Processes (MDPs). Prior work in this setting have established only asymptotic convergence guarantees, leaving open the question of…

Machine Learning · Statistics 2025-12-11 Yang Xu , Washim Uddin Mondal , Vaneet Aggarwal

We study the sample complexity of model-based reinforcement learning (henceforth RL) in general contextual decision processes that require strategic exploration to find a near-optimal policy. We design new algorithms for RL with a generic…

Machine Learning · Computer Science 2019-05-31 Wen Sun , Nan Jiang , Akshay Krishnamurthy , Alekh Agarwal , John Langford

We present a novel off-policy loss function for learning a transition model in model-based reinforcement learning. Notably, our loss is derived from the off-policy policy evaluation objective with an emphasis on correcting distribution…

Machine Learning · Computer Science 2021-03-04 Cameron Voloshin , Nan Jiang , Yisong Yue

The constrained Markov decision process (CMDP) framework emerges as an important reinforcement learning approach for imposing safety or other critical objectives while maximizing cumulative reward. However, the current understanding of how…

Machine Learning · Computer Science 2024-12-11 Tian Tian , Lin F. Yang , Csaba Szepesvári

Partially observable Markov decision processes (POMDPs) are a general framework for sequential decision-making under latent state uncertainty, yet learning in POMDPs is intractable in the worst case. Motivated by sensing and probing…

Machine Learning · Computer Science 2026-01-27 Ming Shi , Yingbin Liang , Ness B. Shroff