English
Related papers

Related papers: PAC-Bayesian Reinforcement Learning Trains General…

200 papers

We present a family of novel block-sample MAC-Bayes bounds (mean approximately correct). While PAC-Bayes bounds (probably approximately correct) typically give bounds for the generalization error that hold with high probability, MAC-Bayes…

Machine Learning · Computer Science 2026-02-16 Matthias Frey , Jingge Zhu , Michael C. Gastpar

Active learning is a framework in which the learning machine can select the samples to be used for training. This technique is promising, particularly when the cost of data acquisition and labeling is high. In active learning, determining…

Machine Learning · Statistics 2020-05-18 Hideaki Ishibashi , Hideitsu Hino

The ultimate performance of machine learning algorithms for classification tasks is usually measured in terms of the empirical error probability (or accuracy) based on a testing dataset. Whereas, these algorithms are optimized through the…

Machine Learning · Computer Science 2021-12-13 Matias Vera , Leonardo Rey Vega , Pablo Piantanida

In this paper we study a model-based approach to calculating approximately optimal policies in Markovian Decision Processes. In particular, we derive novel bounds on the loss of using a policy derived from a factored linear model, a class…

Machine Learning · Statistics 2016-09-22 Bernardo Ávila Pires , Csaba Szepesvári

In this work, we propose Behavior-Guided Actor-Critic (BAC), an off-policy actor-critic deep RL algorithm. BAC mathematically formulates the behavior of the policy through autoencoders by providing an accurate estimation of how frequently…

Machine Learning · Computer Science 2021-04-12 Ammar Fayad , Majd Ibrahim

We are interested in how to design reinforcement learning agents that provably reduce the sample complexity for learning new tasks by transferring knowledge from previously-solved ones. The availability of solutions to related problems…

Machine Learning · Computer Science 2020-07-03 Andrea Tirinzoni , Riccardo Poiani , Marcello Restelli

We exhibit a strong link between frequentist PAC-Bayesian risk bounds and the Bayesian marginal likelihood. That is, for the negative log-likelihood loss function, we show that the minimization of PAC-Bayesian generalization risk bounds…

Machine Learning · Statistics 2017-02-14 Pascal Germain , Francis Bach , Alexandre Lacoste , Simon Lacoste-Julien

Physics-informed machine learning (PIML) integrates mechanistic knowledge, typically in the form of partial differential equations (PDE), into data-driven models. Despite strong empirical performance, its statistical generalisation…

Machine Learning · Computer Science 2026-05-27 Thien V. Nguyen , Amaury Habrard , Benjamin Guedj

Despite its wide use and empirical successes, the theoretical understanding and study of the behaviour and performance of the variational autoencoder (VAE) have only emerged in the past few years. We contribute to this recent line of work…

Machine Learning · Computer Science 2022-02-24 Badr-Eddine Chérief-Abdellatif , Yuyang Shi , Arnaud Doucet , Benjamin Guedj

In this paper we derive a PAC-Bayesian error bound for autonomous stochastic LTI state-space models. The motivation for deriving such error bounds is that they will allow deriving similar error bounds for more general dynamical systems,…

We present a general approach to deriving bounds on the generalization error of randomized learning algorithms. Our approach can be used to obtain bounds on the average generalization error as well as bounds on its tail probabilities, both…

Information Theory · Computer Science 2020-09-10 Fredrik Hellström , Giuseppe Durisi

Soft Actor-Critic (SAC) is an off-policy actor-critic reinforcement learning algorithm, essentially based on entropy regularization. SAC trains a policy by maximizing the trade-off between expected return and entropy (randomness in the…

Machine Learning · Computer Science 2021-09-27 Chayan Banerjee , Zhiyong Chen , Nasimul Noman

We address the problem of Bayesian reinforcement learning using efficient model-based online planning. We propose an optimism-free Bayes-adaptive algorithm to induce deeper and sparser exploration with a theoretical bound on its performance…

Machine Learning · Computer Science 2020-06-30 Divya Grover , Debabrota Basu , Christos Dimitrakakis

Model-free deep reinforcement learning has achieved great success in many domains, such as video games, recommendation systems and robotic control tasks. In continuous control tasks, widely used policies with Gaussian distributions results…

Machine Learning · Computer Science 2023-06-05 Lingwei Peng , Hui Qian , Zhebang Shen , Chao Zhang , Fei Li

In this paper, we present refined probabilistic bounds on empirical reward estimates for off-policy learning in bandit problems. We build on the PAC-Bayesian bounds from Seldin et al. (2010) and improve on their results using a new…

Machine Learning · Statistics 2025-02-18 Amaury Gouverneur , Tobias J. Oechtering , Mikael Skoglund

Reinforcement learning and data-driven autonomous controllers are commonly evaluated using cumulative reward and empirical success frequency under finite simulation trajectories. However, such empirical metrics do not necessarily provide…

Machine Learning · Computer Science 2026-05-28 Fei Jiang , Lei Yang

This work discusses how to derive upper bounds for the expected generalisation error of supervised learning algorithms by means of the chaining technique. By developing a general theoretical framework, we establish a duality between…

Machine Learning · Statistics 2022-07-01 Eugenio Clerico , Amitis Shidani , George Deligiannidis , Arnaud Doucet

Security in machine learning is fragile when data are exfiltrated or perturbed, yet existing frameworks rarely connect the definition and analysis of the security to learnability. In this work, we develop a theory of secure learning…

Quantum Physics · Physics 2025-11-05 Jeongho Bang

Goldwasser et al. (2021) recently proposed the setting of PAC verification, where a hypothesis (machine learning model) that purportedly satisfies the agnostic PAC learning objective is verified using an interactive proof. In this paper we…

Machine Learning · Statistics 2023-09-06 Saachi Mutreja , Jonathan Shafer

We present two alternative ways to apply PAC-Bayesian analysis to sequences of dependent random variables. The first is based on a new lemma that enables to bound expectations of convex functions of certain dependent random variables by…

Machine Learning · Computer Science 2011-05-20 Yevgeny Seldin , François Laviolette , John Shawe-Taylor , Jan Peters , Peter Auer