English
Related papers

Related papers: A maximum-entropy approach to off-policy evaluatio…

200 papers

We investigate the problem of best policy identification in discounted linear Markov Decision Processes in the fixed confidence setting under a generative model. We first derive an instance-specific lower bound on the expected number of…

Machine Learning · Computer Science 2022-08-12 Jerome Taupin , Yassir Jedra , Alexandre Proutiere

We study learning optimal policies from a logged dataset, i.e., offline RL, with function approximation. Despite the efforts devoted, existing algorithms with theoretic finite-sample guarantees typically assume exploratory data coverage or…

Machine Learning · Computer Science 2023-05-25 Chenjie Mao

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 develop a…

Machine Learning · Statistics 2022-10-18 Rui Miao , Zhengling Qi , Xiaoke Zhang

Off-policy evaluation (OPE) is a fundamental task in reinforcement learning (RL). In the classic setting of linear OPE, finite-sample guarantees often take the form $$ \textrm{Evaluation error} \le \textrm{poly}(C^\pi, d,…

Machine Learning · Computer Science 2026-01-28 Philip Amortila , Audrey Huang , Akshay Krishnamurthy , Nan Jiang

We study the problem of synthesizing a policy that maximizes the entropy of a Markov decision process (MDP) subject to a temporal logic constraint. Such a policy minimizes the predictability of the paths it generates, or dually, maximizes…

Optimization and Control · Mathematics 2019-06-17 Yagiz Savas , Melkior Ornik , Murat Cubuktepe , Mustafa O. Karabag , Ufuk Topcu

We present a method for a certain class of Markov Decision Processes (MDPs) that can relate the optimal policy back to one or more reward sources in the environment. For a given initial state, without fully computing the value function,…

Machine Learning · Computer Science 2018-06-12 Josh Bertram , Peng Wei

We study the problem of efficient exploration in order to learn an accurate model of an environment, modeled as a Markov decision process (MDP). Efficient exploration in this problem requires the agent to identify the regions in which…

Markov decision processes (MDPs) are used to model a wide variety of applications ranging from game playing over robotics to finance. Their optimal policy typically maximizes the expected sum of rewards given at each step of the decision…

Machine Learning · Computer Science 2025-05-26 Maximilian Nägele , Jan Olle , Thomas Fösel , Remmy Zen , Florian Marquardt

In this paper, we consider reinforcement learning of Markov Decision Processes (MDP) with peak constraints, where an agent chooses a policy to optimize an objective and at the same time satisfy additional constraints. The agent has to take…

Optimization and Control · Mathematics 2019-12-09 Ather Gattami

The key assumption underlying linear Markov Decision Processes (MDPs) is that the learner has access to a known feature map $\phi(x, a)$ that maps state-action pairs to $d$-dimensional vectors, and that the rewards and transitions are…

Machine Learning · Computer Science 2023-09-20 Noah Golowich , Ankur Moitra , Dhruv Rohatgi

This paper aims to establish an entropy-regularized value-based reinforcement learning method that can ensure the monotonic improvement of policies at each policy update. Unlike previously proposed lower-bounds on policy improvement in…

Machine Learning · Computer Science 2020-08-26 Lingwei Zhu , Takamitsu Matsubara

Suppose an agent is in a (possibly unknown) Markov Decision Process in the absence of a reward signal, what might we hope that an agent can efficiently learn to do? This work studies a broad class of objectives that are defined solely as…

Machine Learning · Computer Science 2019-01-29 Elad Hazan , Sham M. Kakade , Karan Singh , Abby Van Soest

We study the problem of infinite-horizon average-reward reinforcement learning with linear Markov decision processes (MDPs). The associated Bellman operator of the problem not being a contraction makes the algorithm design challenging.…

Machine Learning · Statistics 2025-03-12 Kihyuk Hong , Woojin Chae , Yufan Zhang , Dabeen Lee , Ambuj Tewari

We study reinforcement learning (RL) with linear function approximation. For episodic time-inhomogeneous linear Markov decision processes (linear MDPs) whose transition probability can be parameterized as a linear function of a given…

Machine Learning · Computer Science 2023-11-07 Jiafan He , Heyang Zhao , Dongruo Zhou , Quanquan Gu

We introduce a novel class of algorithms to efficiently approximate the unknown return distributions in policy evaluation problems from distributional reinforcement learning (DRL). The proposed distributional dynamic programming algorithms…

Machine Learning · Statistics 2024-07-22 Julian Gerstenberg , Ralph Neininger , Denis Spiegel

Partially-observable Markov decision processes (POMDPs) with discounted-sum payoff are a standard framework to model a wide range of problems related to decision making under uncertainty. Traditionally, the goal has been to obtain policies…

Artificial Intelligence · Computer Science 2018-05-01 Krishnendu Chatterjee , Adrián Elgyütt , Petr Novotný , Owen Rouillé

We propose and study a general framework for regularized Markov decision processes (MDPs) where the goal is to find an optimal policy that maximizes the expected discounted total reward plus a policy regularization term. The extant…

Machine Learning · Statistics 2019-10-22 Xiang Li , Wenhao Yang , Zhihua Zhang

We present an alternative view for the study of optimal control of partially observed Markov Decision Processes (POMDPs). We first revisit the traditional (and by now standard) separated-design method of reducing the problem to fully…

Optimization and Control · Mathematics 2024-12-20 Serdar Yüksel

Off-policy evaluation (OPE) in reinforcement learning allows one to evaluate novel decision policies without needing to conduct exploration, which is often costly or otherwise infeasible. We consider for the first time the semiparametric…

Machine Learning · Computer Science 2020-06-08 Nathan Kallus , Masatoshi Uehara

We introduce learning and planning algorithms for average-reward MDPs, including 1) the first general proven-convergent off-policy model-free control algorithm without reference states, 2) the first proven-convergent off-policy model-free…

Machine Learning · Computer Science 2021-06-29 Yi Wan , Abhishek Naik , Richard S. Sutton