English
Related papers

Related papers: Hilbert Space Embeddings of POMDPs

200 papers

This paper introduces an approach for detecting differences in the first-order structures of spatial point patterns. The proposed approach leverages the kernel mean embedding in a novel way by introducing its approximate version tailored to…

Methodology · Statistics 2020-06-15 Raif M. Rustamov , James T. Klosowski

Transfer operators such as the Perron--Frobenius or Koopman operator play an important role in the global analysis of complex dynamical systems. The eigenfunctions of these operators can be used to detect metastable sets, to project the…

Dynamical Systems · Mathematics 2019-12-02 Stefan Klus , Ingmar Schuster , Krikamol Muandet

We propose a novel framework for incorporating qualitative data into quantitative models for causal estimation. Previous methods use categorical variables derived from qualitative data to build quantitative models. However, this approach…

Machine Learning · Computer Science 2023-08-24 Anirban Mukherjee , Hannah H. Chang

In this paper we combine the theory of reproducing kernel Hilbert spaces with the field of collocation methods to solve boundary value problems with special emphasis on reproducing property of kernels. From the reproducing property of…

Numerical Analysis · Mathematics 2019-03-26 Babak Azarnavid , Mahdi Emamjome , Mohammad Nabati , Saeid Abbasbandy

Policy-gradient methods have received increased attention recently as a mechanism for learning to act in partially observable environments. They have shown promise for problems admitting memoryless policies but have been less successful…

Machine Learning · Computer Science 2025-12-08 Douglas Aberdeen , Jonathan Baxter

The use of deep neural networks as function approximators has led to striking progress for reinforcement learning algorithms and applications. Yet the knowledge we have on decision boundary geometry and the loss landscape of neural policies…

Machine Learning · Computer Science 2021-12-17 Ezgi Korkmaz

This article introduces the theory of offline reinforcement learning in large state spaces, where good policies are learned from historical data without online interactions with the environment. Key concepts introduced include expressivity…

Machine Learning · Computer Science 2025-10-07 Nan Jiang , Tengyang Xie

Motivated by many application problems, we consider Markov decision processes (MDPs) with a general loss function and unknown parameters. To mitigate the epistemic uncertainty associated with unknown parameters, we take a Bayesian approach…

Machine Learning · Computer Science 2025-10-02 Xiaoshuang Wang , Yifan Lin , Enlu Zhou

In most real-world reinforcement learning applications, state information is only partially observable, which breaks the Markov decision process assumption and leads to inferior performance for algorithms that conflate observations with…

Machine Learning · Computer Science 2024-06-12 Hongming Zhang , Tongzheng Ren , Chenjun Xiao , Dale Schuurmans , Bo Dai

A defining feature of sampling-based motion planning is the reliance on an implicit representation of the state space, which is enabled by a set of probing samples. Traditionally, these samples are drawn either probabilistically or…

Robotics · Computer Science 2019-03-13 Brian Ichter , James Harrison , Marco Pavone

Decision-making under uncertainty is a crucial ability for autonomous systems. In its most general form, this problem can be formulated as a Partially Observable Markov Decision Process (POMDP). The solution policy of a POMDP can be…

Robotics · Computer Science 2019-04-09 Sung-Kyun Kim , Rohan Thakker , Ali-akbar Agha-mohammadi

General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, reinforcement learning is well-developed for small…

Machine Learning · Computer Science 2009-12-30 Marcus Hutter

We consider a protocol to perform the optimal quantum state discrimination of $N$ linearly independent non-orthogonal pure quantum states and present a computational code. Through the extension of the original Hilbert space, it is possible…

Quantum Physics · Physics 2016-09-08 Wilson R. M. Rabelo , Alexandre G. Rodrigues , Reinaldo O. Vianna

This paper studies the probabilistic function approximation problem over reproducing kernel Hilbert spaces. We show the existence and uniqueness of the optimizer under mild assumptions. Furthermore, we generalize the celebrated representer…

Functional Analysis · Mathematics 2025-07-16 Dongwei Chen , Kai-Hsiang Wang

We propose a novel approach for pixel classification in hyperspectral images, leveraging on both the spatial and spectral information in the data. The introduced method relies on a recently proposed framework for learning on distributions…

Computer Vision and Pattern Recognition · Computer Science 2016-05-31 Gianni Franchi , Jesus Angulo , Dino Sejdinovic

Off-policy Reinforcement Learning (RL) holds the promise of better data efficiency as it allows sample reuse and potentially enables safe interaction with the environment. Current off-policy policy gradient methods either suffer from high…

Machine Learning · Computer Science 2021-06-09 Samuele Tosatto , João Carvalho , Jan Peters

This expository article presents the approach to statistical machine learning based on reproducing kernel Hilbert spaces. The basic framework is introduced for scalar-valued learning and then extended to operator learning. Finally, learning…

Machine Learning · Computer Science 2025-09-24 Lorenzo Rosasco

This paper extends the framework of partially observable Markov decision processes (POMDPs) to multi-agent settings by incorporating the notion of agent models into the state space. Agents maintain beliefs over physical states of the…

Artificial Intelligence · Computer Science 2011-09-13 P. Doshi , P. J. Gmytrasiewicz

In this paper, we establish minimax optimal rates of convergence for prediction in a semi-functional linear model that consists of a functional component and a less smooth nonparametric component. Our results reveal that the smoother…

Statistics Theory · Mathematics 2021-11-01 Keli Guo , Jun Fan , Lixing Zhu

We consider the problem of finding good finite-horizon policies for POMDPs under the expected reward metric. The policies considered are {em free finite-memory policies with limited memory}; a policy is a mapping from the space of…

Artificial Intelligence · Computer Science 2013-01-30 Christopher Lusena , Tong Li , Shelia Sittinger , Chris Wells , Judy Goldsmith