An Expectation Maximization Algorithm for Continuous Markov Decision Processes with Arbitrary Reward

An Expectation Maximization Algorithm for Continuous Markov Decision Processes with Arbitrary Reward

We derive a new expectation maximization algorithm for policy optimization in linear Gaussian Markov decision processes, where the reward function is parameterised in terms of a flexible mixture of Gaussians. This approach exploits both analytical tractability and numerical optimization. Consequentl...

Szczegółowa specyfikacja

Opis bibliograficzny
Główni autorzy:	Hoffman, M, de Freitas, N, Doucet, A, Peters, J
Format:	Journal article
Wydane:	2009

Podobne zapisy

An expectation maximization algorithm for continuous Markov decision processes with arbitrary rewards
od: Hoffman, M, i wsp.
Wydane: (2009)

Learning to maximize reward rate: a model based on semi-Markov decision processes
od: Arash eKhodadadi, i wsp.
Wydane: (2014-05-01)

Expectation-maximization algorithms for inference in Dirichlet processes mixture
od: Kimura, T, i wsp.
Wydane: (2013)

Policy Iteration for Continuous-Time Average Reward Markov Decision Processes in Polish Spaces
od: Quanxin Zhu, i wsp.
Wydane: (2009-01-01)

New inference strategies for solving Markov Decision Processes using reversible jump MCMC
od: Hoffman, M, i wsp.
Wydane: (2009)

New inference strategies for solving Markov Decision Processes using reversible jump MCMC
od: Hoffman, M, i wsp.
Wydane: (2009)

An Online Expectation-Maximization Algorithm for Changepoint Models
od: Yildirim, S, i wsp.
Wydane: (2013)

Deterministic Discounted Markov Decision Processes with Fuzzy Rewards/Costs
od: Hugo Cruz-Suárez, i wsp.
Wydane: (2023-09-01)

Inference Strategies for Solving Semi−Markov Decision Processes
od: Hoffman, M, i wsp.
Wydane: (2012)

Markov decision processes in minimization of expected costs
od: Marija Rukav, i wsp.
Wydane: (2014-12-01)

Online Expectation-Maximization type algorithms for parameter estimation in general state space models
od: Andrieu, C, i wsp.
Wydane: (2003)

Novel Adaptive Hidden Markov Model Utilizing Expectation–Maximization Algorithm for Advanced Pipeline Leak Detection
od: Omid Zadehbagheri, i wsp.
Wydane: (2024-09-01)

Simulation-based optimization of Markov reward processes
Wydane: (2003)

Entropic Regularization of Markov Decision Processes
od: Boris Belousov, i wsp.
Wydane: (2019-07-01)

Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm.
od: Zhang, Y, i wsp.
Wydane: (2001)

Inhibitor Petri Net that Executes an Arbitrary Given Markov Normal Algorithm
od: D. A. Zaitsev
Wydane: (2011-12-01)

Simulation-based algorithms for Markov decision processes /
od: Chang, Hyeong Soo
Wydane: (2007)

Maximal cuts in arbitrary dimension
od: Jorrit Bosma, i wsp.
Wydane: (2017-08-01)

Human decision making balances reward maximization and policy compression.
od: Lucy Lai, i wsp.
Wydane: (2024-04-01)

Efficient algorithms for training the parameters of hidden Markov models using stochastic expectation maximization (EM) training and Viterbi training
od: Meyer Irmtraud M, i wsp.
Wydane: (2010-12-01)

Algorithmic aspects of mean–variance optimization in Markov decision processes
od: Tsitsiklis, John N, i wsp.
Wydane: (2017)

Covert expectation-of-reward in rat ventral striatum at decision points
od: Matthijs A A Van Der Meer, i wsp.
Wydane: (2009-02-01)

Gauss process state-space model optimization algorithm with expectation maximization
od: Hongqiang Liu, i wsp.
Wydane: (2019-07-01)

Minimizing the expected search time of finding the hidden object by maximizing the discount effort reward search
od: Mohamed Abd Allah El-Hadidy, i wsp.
Wydane: (2020-01-01)

Analyticity of entropy rates of continuous-state hidden Markov models
od: Tadic, V, i wsp.
Wydane: (2019)

Markov decision processes /
od: 352167 White, D. J.
Wydane: (1993)

An Improved Expectation–Maximization Bayesian Algorithm for GWAS
od: Ganwen Zhang, i wsp.
Wydane: (2024-06-01)

A policy gradient method for semi-Markov decision processes with application to call admission control
od: Singh, S, i wsp.
Wydane: (2007)

Expectation-Maximization Method for EEG-Based Continuous Cursor Control
od: Yixiao Wang, i wsp.
Wydane: (2007-01-01)

Expectation-Maximization Method for EEG-Based Continuous Cursor Control
od: Guan Cuntai, i wsp.
Wydane: (2007-01-01)

Polynomial algorithms for the Maximal Pairing Problem: efficient phylogenetic targeting on arbitrary trees
od: Stadler Peter F, i wsp.
Wydane: (2010-06-01)

Reward is not reward: Differential impacts of primary and secondary rewards on expectation, outcome, and prediction error in the human brain's reward processing regions
od: Martin Ulrich, i wsp.
Wydane: (2023-12-01)

Modeling eye movement in dynamic interactive tasks for maximizing situation awareness based on Markov decision process
od: Shuo Ma, i wsp.
Wydane: (2022-08-01)

Expected utility and reward value representations in a probabilistic decision task
od: Mccabe, C, i wsp.
Wydane: (2006)

An Improved Mixture Model of Gaussian Processes and Its Classification Expectation–Maximization Algorithm
od: Yurong Xie, i wsp.
Wydane: (2023-05-01)

The modulation of information processing by reward expectation and spatial attention
od: Baines, S, i wsp.
Wydane: (2010)

Extension of emission expectation maximization lookalike algorithms to Bayesian algorithms
od: Gengsheng L. Zeng, i wsp.
Wydane: (2019-11-01)

Tuning the speed-accuracy trade-off to maximize reward rate in multisensory decision-making
od: Jan Drugowitsch, i wsp.
Wydane: (2015-06-01)

A Heavy Tailed Expectation Maximization Hidden Markov Random Field Model with Applications to Segmentation of MRI
od: Diego Castillo-Barnes, i wsp.
Wydane: (2017-11-01)

Bounds for Markov Decision Processes
od: Desai, Vijay V., i wsp.
Wydane: (2019)