English
Related papers

Related papers: A Tale of Sampling and Estimation in Discounted Re…

200 papers

The optimal objective is a fundamental aspect of reinforcement learning (RL), as it determines how policies are evaluated and optimized. While total return maximization is the ideal objective in RL, discounted return maximization is the…

Machine Learning · Computer Science 2025-03-19 Shuyu Yin , Fei Wen , Peilin Liu , Tao Luo

We consider the problem of learning a policy for a Markov decision process consistent with data captured on the state-actions pairs followed by the policy. We assume that the policy belongs to a class of parameterized policies which are…

Optimization and Control · Mathematics 2017-01-24 Manjesh K. Hanawal , Hao Liu , Henghui Zhu , Ioannis Ch. Paschalidis

In many real-world learning scenarios, features are only acquirable at a cost constrained under a budget. In this paper, we propose a novel approach for cost-sensitive feature acquisition at the prediction-time. The suggested method…

Machine Learning · Computer Science 2019-02-19 Mohammad Kachuee , Orpaz Goldstein , Kimmo Karkkainen , Sajad Darabi , Majid Sarrafzadeh

Projected policy gradient under the simplex parameterization, policy gradient and natural policy gradient under the softmax parameterization, are fundamental algorithms in reinforcement learning. There have been a flurry of recent…

Optimization and Control · Mathematics 2024-04-12 Jiacai Liu , Wenye Li , Ke Wei

This note re-visits the rolling-horizon control approach to the problem of a Markov decision process (MDP) with infinite-horizon discounted expected reward criterion. Distinguished from the classical value-iteration approach, we develop an…

Optimization and Control · Mathematics 2022-06-07 Hyeong Soo Chang

Many policy-based reinforcement learning (RL) algorithms can be viewed as instantiations of approximate policy iteration (PI), i.e., where policy improvement and policy evaluation are both performed approximately. In applications where the…

Machine Learning · Computer Science 2023-06-29 Yashaswini Murthy , Mehrdad Moharrami , R. Srikant

Discount regularization, using a shorter planning horizon when calculating the optimal policy, is a popular choice to restrict planning to a less complex set of policies when estimating an MDP from sparse or noisy data (Jiang et al., 2015).…

Machine Learning · Computer Science 2023-06-21 Sarah Rathnam , Sonali Parbhoo , Weiwei Pan , Susan A. Murphy , Finale Doshi-Velez

Specifying a Reinforcement Learning (RL) task involves choosing a suitable planning horizon, which is typically modeled by a discount factor. It is known that applying RL algorithms with a lower discount factor can act as a regularizer,…

Machine Learning · Computer Science 2020-07-07 Ron Amit , Ron Meir , Kamil Ciosek

Markov control algorithms that perform smooth, non-greedy updates of the policy have been shown to be very general and versatile, with policy gradient and Expectation Maximisation algorithms being particularly popular. For these algorithms,…

Systems and Control · Computer Science 2012-02-20 Thomas Furmston , David Barber

Reinforcement learning algorithms typically rely on the assumption that the environment dynamics and value function can be expressed in terms of a Markovian state representation. However, when state information is only partially observable,…

We study the problem of learning Markov decision processes with finite state and action spaces when the transition probability distributions and loss functions are chosen adversarially and are allowed to change with time. We introduce an…

Machine Learning · Computer Science 2013-03-14 Yasin Abbasi-Yadkori , Peter L. Bartlett , Csaba Szepesvari

We study methods based on reproducing kernel Hilbert spaces for estimating the value function of an infinite-horizon discounted Markov reward process (MRP). We study a regularized form of the kernel least-squares temporal difference (LSTD)…

Machine Learning · Statistics 2021-09-27 Yaqi Duan , Mengdi Wang , Martin J. Wainwright

In this paper we consider the problem of learning an $\epsilon$-optimal policy for a discounted Markov Decision Process (MDP). Given an MDP with $S$ states, $A$ actions, the discount factor $\gamma \in (0,1)$, and an approximation threshold…

Machine Learning · Computer Science 2020-12-25 Zihan Zhang , Yuan Zhou , Xiangyang Ji

We study reinforcement learning (RL) with linear function approximation where the underlying transition probability kernel of the Markov decision process (MDP) is a linear mixture model (Jia et al., 2020; Ayoub et al., 2020; Zhou et al.,…

Machine Learning · Computer Science 2021-01-08 Dongruo Zhou , Quanquan Gu , Csaba Szepesvari

Traditional methods for unsupervised learning of finite mixture models require to evaluate the likelihood of all components of the mixture. This becomes computationally prohibitive when the number of components is large, as it is, for…

Machine Learning · Computer Science 2021-10-12 Milan Papež , Tomáš Pevný , Václav Šmídl

Given a sequence of observations from a discrete-time, finite-state hidden Markov model, we would like to estimate the sampling distribution of a statistic. The bootstrap method is employed to approximate the confidence regions of a…

Computation · Statistics 2009-09-29 Cheng-Der Fuh , Inchi Hu

We consider the problem: is the optimal expected total reward to reach a goal state in a partially observable Markov decision process (POMDP) below a given threshold? We tackle this -- generally undecidable -- problem by computing…

Artificial Intelligence · Computer Science 2022-01-24 Alexander Bork , Joost-Pieter Katoen , Tim Quatmann

In this article we consider risk-sensitive control of semi-Markov processes with a discrete state space. We consider general utility functions and discounted cost in the optimization criteria. We consider random finite horizon and infinite…

Optimization and Control · Mathematics 2021-01-13 Arnab Bhabak , Subhamay Saha

Reinforcement learning generalizes multi-armed bandit problems with additional difficulties of a longer planning horizon and unknown transition kernel. We explore a black-box reduction from discounted infinite-horizon tabular reinforcement…

Machine Learning · Computer Science 2024-03-12 Ian A. Kash , Lev Reyzin , Zishun Yu

Based on information theory, we present a method to determine an optimal Markov approximation for modelling and prediction from time series data. The method finds a balance between minimal modelling errors by taking as much as possible…

Chaotic Dynamics · Physics 2013-05-29 Detlef Holstein , Holger Kantz