English
Related papers

Related papers: Bayesian Bellman Operators

200 papers

We show that the popular reinforcement learning (RL) strategy of estimating the state-action value (Q-function) by minimizing the mean squared Bellman error leads to a regression problem with confounding, the inputs and output noise being…

Machine Learning · Computer Science 2022-12-01 Yutian Chen , Liyuan Xu , Caglar Gulcehre , Tom Le Paine , Arthur Gretton , Nando de Freitas , Arnaud Doucet

A large class of stochastic programs involve optimizing an expectation taken with respect to an underlying distribution that is unknown in practice. One popular approach to addressing the distributional uncertainty, known as the…

Optimization and Control · Mathematics 2017-08-30 Di Wu , Helin Zhu , Enlu Zhou

This paper presents a recursive reasoning formalism of Bayesian optimization (BO) to model the reasoning process in the interactions between boundedly rational, self-interested agents with unknown, complex, and costly-to-evaluate payoff…

Machine Learning · Computer Science 2020-07-01 Zhongxiang Dai , Yizhou Chen , Kian Hsiang Low , Patrick Jaillet , Teck-Hua Ho

Bayesian Optimization (BO) is a sample-efficient black-box optimizer commonly used in search spaces where hyperparameters are independent. However, in many practical AutoML scenarios, there will be dependencies among hyperparameters,…

Machine Learning · Computer Science 2025-01-28 Jiaxing Li , Wei Liu , Chao Xue , Yibing Zhan , Xiaoxing Wang , Weifeng Liu , Dacheng Tao

Offline reinforcement learning (RL) aims at learning policies from previously collected static trajectory data without interacting with the real environment. Recent works provide a novel perspective by viewing offline RL as a generic…

Machine Learning · Computer Science 2022-10-19 Kerong Wang , Hanye Zhao , Xufang Luo , Kan Ren , Weinan Zhang , Dongsheng Li

Bayesian optimization (BO) is a class of sample-efficient global optimization methods, where a probabilistic model conditioned on previous observations is used to determine future evaluations via the optimization of an acquisition function.…

Machine Learning · Computer Science 2020-06-22 Eric Hans Lee , David Eriksson , Bolong Cheng , Michael McCourt , David Bindel

Large Language Models (LLMs) often suffer from overconfidence during inference, particularly when adapted to downstream domain-specific tasks with limited data. Previous work addresses this issue by employing approximate Bayesian estimation…

Machine Learning · Computer Science 2025-01-28 Yibin Wang , Haizhou Shi , Ligong Han , Dimitris Metaxas , Hao Wang

We introduce a novel framework for analyzing reinforcement learning (RL) in continuous state-action spaces, and use it to prove fast rates of convergence in both off-line and on-line settings. Our analysis highlights two key stability…

Machine Learning · Computer Science 2024-01-11 Yaqi Duan , Martin J. Wainwright

Inverse problems are ubiquitous because they formalize the integration of data with mathematical models. In many scientific applications the forward model is expensive to evaluate, and adjoint computations are difficult to employ; in this…

Dynamical Systems · Mathematics 2021-11-05 G. A. Pavliotis , A. M. Stuart , U. Vaes

Reinforcement learning (RL) based investment strategies have been widely adopted in portfolio management (PM) in recent years. Nevertheless, most RL-based approaches may often emphasize on pursuing returns while ignoring the risks of the…

Portfolio Management · Quantitative Finance 2023-06-13 Zhenglong Li , Hejun Huang , Vincent Tam

This paper introduces new optimality-preserving operators on Q-functions. We first describe an operator for tabular representations, the consistent Bellman operator, which incorporates a notion of local policy consistency. We show that this…

Artificial Intelligence · Computer Science 2015-12-16 Marc G. Bellemare , Georg Ostrovski , Arthur Guez , Philip S. Thomas , Rémi Munos

Bayesian inverse reinforcement learning (IRL) methods are ideal for safe imitation learning, as they allow a learning agent to reason about reward uncertainty and the safety of a learned policy. However, Bayesian IRL is computationally…

Machine Learning · Computer Science 2019-12-11 Daniel S. Brown , Scott Niekum

The Bayesian expected power (BEP) has become increasingly popular in sample size determination and assessment of the probability of success (POS) for a future trial. The BEP takes into consideration the uncertainty around the parameters…

Methodology · Statistics 2020-07-01 Fang Liu

In this paper, we study the Bayesian risk-averse formulation in reinforcement learning (RL). To address the epistemic uncertainty due to a lack of data, we adopt the Bayesian Risk Markov Decision Process (BRMDP) to account for the parameter…

Machine Learning · Computer Science 2025-09-18 Yuhao Wang , Enlu Zhou

Recurrent neural networks (RNNs) are a powerful approach for time series prediction. However, their performance is strongly affected by their architecture and hyperparameter settings. The architecture optimization of RNNs is a…

Machine Learning · Computer Science 2021-04-26 Andrés Camero , Hao Wang , Enrique Alba , Thomas Bäck

While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the…

Machine Learning · Computer Science 2022-12-29 Tim G. J. Rudner , Vitchyr H. Pong , Rowan McAllister , Yarin Gal , Sergey Levine

Bayesian optimization (BO) is a successful methodology to optimize black-box functions that are expensive to evaluate. While traditional methods optimize each black-box function in isolation, there has been recent interest in speeding up BO…

Machine Learning · Statistics 2019-09-30 Valerio Perrone , Huibin Shen , Matthias Seeger , Cedric Archambeau , Rodolphe Jenatton

Capturing latent variations ("contexts") is key to deploying reinforcement-learning (RL) agents beyond their training regime. We recast context-based RL as a dual inference-control problem and formally characterize two properties and their…

Machine Learning · Computer Science 2025-07-28 Yuliang Gu , Hongpeng Cao , Marco Caccamo , Naira Hovakimyan

This paper introduces a model-free real-time optimization (RTO) framework based on unconstrained Bayesian optimization with embedded constraint control. The main contribution lies in demonstrating how this approach simplifies the black-box…

Optimization and Control · Mathematics 2024-02-29 Dinesh Krishnamoorthy

Automatic Machine Learning (Auto-ML) systems tackle the problem of automating the design of prediction models or pipelines for data science. In this paper, we present Lifelong Bayesian Optimization (LBO), an online, multitask Bayesian…

Machine Learning · Statistics 2019-06-24 Yao Zhang , James Jordon , Ahmed M. Alaa , Mihaela van der Schaar