English
Related papers

Related papers: Hilbert Space Embeddings of POMDPs

200 papers

We propose a new, nonparametric approach to estimating the value function in reinforcement learning. This approach makes use of a recently developed representation of conditional distributions as functions in a reproducing kernel Hilbert…

Machine Learning · Computer Science 2012-10-19 Steffen Grünewälder , Luca Baldassarre , Massimiliano Pontil , Arthur Gretton , Guy Lever

We study reinforcement learning with function approximation for large-scale Partially Observable Markov Decision Processes (POMDPs) where the state space and observation space are large or even continuous. Particularly, we consider Hilbert…

Machine Learning · Computer Science 2022-06-27 Masatoshi Uehara , Ayush Sekhari , Jason D. Lee , Nathan Kallus , Wen Sun

We propose a new, nonparametric approach to learning and representing transition dynamics in Markov decision processes (MDPs), which can be combined easily with dynamic programming methods for policy optimisation and value estimation. This…

Machine Learning · Computer Science 2012-06-22 Steffen Grunewalder , Guy Lever , Luca Baldassarre , Massi Pontil , Arthur Gretton

We propose an (offline) multi-dimensional distributional reinforcement learning framework (KE-DRL) that leverages Hilbert space mappings to estimate the kernel mean embedding of the multi-dimensional value distribution under a proposed…

Machine Learning · Computer Science 2026-01-28 Mehrdad Mohammadi , Qi Zheng , Ruoqing Zhu

Predictive State Representations (PSRs) are an expressive class of models for controlled stochastic processes. PSRs represent state as a set of predictions of future observable events. Because PSRs are defined entirely in terms of…

Machine Learning · Computer Science 2013-09-27 Byron Boots , Geoffrey Gordon , Arthur Gretton

We propose a general framework for policy representation for reinforcement learning tasks. This framework involves finding a low-dimensional embedding of the policy on a reproducing kernel Hilbert space (RKHS). The usage of RKHS based…

Machine Learning · Computer Science 2020-10-16 Bogdan Mazoure , Thang Doan , Tianyu Li , Vladimir Makarenkov , Joelle Pineau , Doina Precup , Guillaume Rabusseau

A Hilbert space embedding of a distribution---in short, a kernel mean embedding---has recently emerged as a powerful tool for machine learning and inference. The basic idea behind this framework is to map distributions into a reproducing…

Machine Learning · Statistics 2020-12-15 Krikamol Muandet , Kenji Fukumizu , Bharath Sriperumbudur , Bernhard Schölkopf

The kernel mean embedding of probability distributions is commonly used in machine learning as an injective mapping from distributions to functions in an infinite dimensional Hilbert space. It allows us, for example, to define a distance…

Quantum Physics · Physics 2019-12-24 Jonas M. Kübler , Krikamol Muandet , Bernhard Schölkopf

Kernel mean embeddings are a popular tool that consists in representing probability measures by their infinite-dimensional mean embeddings in a reproducing kernel Hilbert space. When the kernel is characteristic, mean embeddings can be used…

Machine Learning · Computer Science 2021-06-29 Boris Muzellec , Francis Bach , Alessandro Rudi

We describe a method to perform functional operations on probability distributions of random variables. The method uses reproducing kernel Hilbert space representations of probability distributions, and it is applicable to all operations…

Machine Learning · Statistics 2016-09-14 Bernhard Schölkopf , Krikamol Muandet , Kenji Fukumizu , Jonas Peters

Robot control problems are often structured with a policy function that maps state values into control values, but in many dynamic problems the observed state can have a difficult to characterize relationship with useful policy actions. In…

Machine Learning · Computer Science 2020-05-01 Max Pflueger , Gaurav S. Sukhatme

Nonparametric feature selection in high-dimensional data is an important and challenging problem in statistics and machine learning fields. Most of the existing methods for feature selection focus on parametric or additive models which may…

Methodology · Statistics 2021-03-31 Hang Yu , Yuanjia Wang , Donglin Zeng

Reinforcement Learning has been able to solve many complicated robotics tasks without any need for feature engineering in an end-to-end fashion. However, learning the optimal policy directly from the sensory inputs, i.e the observations,…

We consider policy evaluation in infinite-horizon discounted Markov decision problems (MDPs) with infinite spaces. We reformulate this task a compositional stochastic program with a function-valued decision variable that belongs to a…

Optimization and Control · Mathematics 2020-05-19 Alec Koppel , Garrett Warnell , Ethan Stump , Peter Stone , Alejandro Ribeiro

Data-driven control algorithms use observations of system dynamics to construct an implicit model for the purpose of control. However, in practice, data-driven techniques often require excessive sample sizes, which may be infeasible in…

Systems and Control · Electrical Eng. & Systems 2023-01-10 Adam J. Thorpe , Cyrus Neary , Franck Djeumou , Meeko M. K. Oishi , Ufuk Topcu

In supervised learning with distributional inputs in the two-stage sampling setup, relevant to applications like learning-based medical screening or causal learning, the inputs (which are probability distributions) are not accessible in the…

Machine Learning · Computer Science 2026-01-22 Christian Fiedler

We study Reinforcement Learning for partially observable dynamical systems using function approximation. We propose a new \textit{Partially Observable Bilinear Actor-Critic framework}, that is general enough to include models such as…

Machine Learning · Computer Science 2022-06-27 Masatoshi Uehara , Ayush Sekhari , Jason D. Lee , Nathan Kallus , Wen Sun

Kernel embeddings have emerged as a powerful tool for representing probability measures in a variety of statistical inference problems. By mapping probability measures into a reproducing kernel Hilbert space (RKHS), kernel embeddings enable…

Machine Learning · Statistics 2024-10-31 Dino Sejdinovic

Most algorithms for solving POMDPs iteratively improve a value function that implicitly represents a policy and are said to search in value function space. This paper presents an approach to solving POMDPs that represents a policy…

Artificial Intelligence · Computer Science 2013-02-01 Eric A. Hansen

The reproducing kernel Hilbert space (RKHS) embedding method is a recently introduced estimation approach that seeks to identify the unknown or uncertain function in the governing equations of a nonlinear set of ordinary differential…

Optimization and Control · Mathematics 2020-07-14 Jia Guo , Sai Tej Paruchuri , Andrew J. Kurdila
‹ Prev 1 2 3 10 Next ›