English
Related papers

Related papers: Learning and Planning in Average-Reward Markov Dec…

200 papers

We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive)…

Artificial Intelligence · Computer Science 2017-06-20 Kamyar Azizzadenesheli , Alessandro Lazaric , Animashree Anandkumar

In standard RL, a learner attempts to learn an optimal policy for a Markov Decision Process whose structure (e.g. state space) is known. In online model selection, a learner attempts to learn an optimal policy for an MDP knowing only that…

Machine Learning · Computer Science 2024-11-12 Alireza Masoumian , James R. Wright

We study the problem of Inverse Reinforcement Learning (IRL) with an average-reward criterion. The goal is to recover an unknown policy and a reward function when the agent only has samples of states and actions from an experienced agent.…

Machine Learning · Computer Science 2023-05-25 Feiyang Wu , Jingyang Ke , Anqi Wu

We propose and analyze an alternate approach to off-policy multi-step temporal difference learning, in which off-policy returns are corrected with the current Q-function in terms of rewards, rather than with the target policy in terms of…

Artificial Intelligence · Computer Science 2016-08-12 Anna Harutyunyan , Marc G. Bellemare , Tom Stepleton , Remi Munos

Markov decision processes (MDPs) are widely used in modeling decision making problems in stochastic environments. However, precise specification of the reward functions in MDPs is often very difficult. Recent approaches have focused on…

Artificial Intelligence · Computer Science 2012-02-20 Eunsoo Oh , Kee-Eung Kim

We consider off-policy temporal-difference (TD) learning methods for policy evaluation in Markov decision processes with finite spaces and discounted reward criteria, and we present a collection of convergence results for several…

Machine Learning · Computer Science 2018-03-30 Huizhen Yu

Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to…

Machine Learning · Computer Science 2019-08-13 Scott Fujimoto , David Meger , Doina Precup

Planning under uncertainty is a central problem in the study of automated sequential decision making, and has been addressed by researchers in many different fields, including AI planning, decision analysis, operations research, control…

Artificial Intelligence · Computer Science 2011-05-30 C. Boutilier , T. Dean , S. Hanks

Markov decision processes (MDPs) is viewed as an optimization of an objective function over certain linear operators over general function spaces. A new existence result is established for the existence of optimal policies in general MDPs,…

Machine Learning · Computer Science 2026-04-01 Abhishek Gupta , Aditya Mahajan

We consider Markov Decision Processes (MDPs) where the rewards are unknown and may change in an adversarial manner. We provide an algorithm that achieves state-of-the-art regret bound of $O( \sqrt{\tau (\ln|S|+\ln|A|)T}\ln(T))$, where $S$…

Machine Learning · Computer Science 2019-05-28 Adrian Rivera Cardoso , He Wang , Huan Xu

We study the problem of reinforcement learning in infinite-horizon discounted linear Markov decision processes (MDPs), and propose the first computationally efficient algorithm achieving rate-optimal regret guarantees in this setting. Our…

Machine Learning · Computer Science 2026-03-16 Antoine Moulin , Gergely Neu , Luca Viano

Many real-world applications, such as those in medical domains, recommendation systems, etc, can be formulated as large state space reinforcement learning problems with only a small budget of the number of policy changes, i.e., low…

Machine Learning · Computer Science 2021-01-05 Minbo Gao , Tianle Xie , Simon S. Du , Lin F. Yang

To estimate the value functions of policies from exploratory data, most model-free off-policy algorithms rely on importance sampling, where the use of importance sampling ratios often leads to estimates with severe variance. It is thus…

Machine Learning · Computer Science 2017-02-13 Ashique Rupam Mahmood , Huizhen Yu , Richard S. Sutton

The general sequential decision-making problem, which includes Markov decision processes (MDPs) and partially observable MDPs (POMDPs) as special cases, aims at maximizing a cumulative reward by making a sequence of decisions based on a…

Machine Learning · Computer Science 2024-02-07 Ruiquan Huang , Yingbin Liang , Jing Yang

We study the reinforcement learning problem in the setting of finite-horizon episodic Markov Decision Processes (MDPs) with $S$ states, $A$ actions, and episode length $H$. We propose a model-free algorithm UCB-Advantage and prove that it…

Machine Learning · Computer Science 2020-06-09 Zihan Zhang , Yuan Zhou , Xiangyang Ji

Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, we allow the learning agent to ask for help from a mentor and…

Machine Learning · Computer Science 2025-09-17 Benjamin Plaut , Juan Liévano-Karim , Hanlin Zhu , Stuart Russell

In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy.…

Machine Learning · Computer Science 2022-11-04 Jie Wang , Rui Gao , Hongyuan Zha

We introduce and study constrained Markov Decision Processes (cMDPs) with anytime constraints. An anytime constraint requires the agent to never violate its budget at any point in time, almost surely. Although Markovian policies are no…

Machine Learning · Computer Science 2024-06-14 Jeremy McMahan , Xiaojin Zhu

We study the sample complexity of the plug-in approach for learning $\varepsilon$-optimal policies in average-reward Markov decision processes (MDPs) with a generative model. The plug-in approach constructs a model estimate then computes an…

Machine Learning · Computer Science 2025-02-12 Matthew Zurek , Yudong Chen

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