English
Related papers

Related papers: Multiscale replay: A robust algorithm for stochast…

200 papers

Experience replay (ER) is a crucial component of many deep reinforcement learning (RL) systems. However, uniform sampling from an ER buffer can lead to slow convergence and unstable asymptotic behaviors. This paper introduces Stratified…

Machine Learning · Computer Science 2023-06-21 Varun Kompella , Thomas J. Walsh , Samuel Barrett , Peter Wurman , Peter Stone

Experience replay is widely used in deep reinforcement learning algorithms and allows agents to remember and learn from experiences from the past. In an effort to learn more efficiently, researchers proposed prioritized experience replay…

Machine Learning · Computer Science 2020-02-20 Marc Brittain , Josh Bertram , Xuxi Yang , Peng Wei

Prioritized Experience Replay (PER) is a deep reinforcement learning technique in which agents learn from transitions sampled with non-uniform probability proportionate to their temporal-difference error. We show that any loss function…

Machine Learning · Computer Science 2020-10-23 Scott Fujimoto , David Meger , Doina Precup

Motivated by reduction of computational complexity, this work develops sign-error adaptive filtering algorithms for estimating time-varying system parameters. Different from the previous work on sign-error algorithms, the parameters are…

Optimization and Control · Mathematics 2016-11-17 Araz Hashemi , G. Yin , Le Yi Wang

Efficient learning in the environment with sparse rewards is one of the most important challenges in Deep Reinforcement Learning (DRL). In continuous DRL environments such as robotic arms control, Hindsight Experience Replay (HER) has been…

Artificial Intelligence · Computer Science 2020-02-07 Qiwei He , Liansheng Zhuang , Houqiang Li

The hidden Markov model (HMM) is a widely-used generative model that copes with sequential data, assuming that each observation is conditioned on the state of a hidden Markov chain. In this paper, we derive a novel algorithm to cluster HMMs…

Machine Learning · Computer Science 2012-10-26 Emanuele Coviello , Antoni B. Chan , Gert R. G. Lanckriet

We present a flexible Bayesian semiparametric mixed model for longitudinal data analysis in the presence of potentially high-dimensional categorical covariates. Building on a novel hidden Markov tensor decomposition technique, our proposed…

Methodology · Statistics 2022-08-05 Giorgio Paulon , Peter Müller , Abhra Sarkar

In the infectious disease literature, significant effort has been devoted to studying dynamics at a single scale. For example, compartmental models describing population-level dynamics are often formulated using differential equations. In…

Populations and Evolution · Quantitative Biology 2025-04-16 Yuan Yin , Jennifer A. Flegg , Mark B. Flegg

Stochastic variational inference algorithms are derived for fitting various heteroskedastic time series models. We examine Gaussian, t, and skew-t response GARCH models and fit these using Gaussian variational approximating densities. We…

Computation · Statistics 2023-08-30 Hanwen Xuan , Luca Maestrini , Feng Chen , Clara Grazian

Experience replay is one of the most commonly used approaches to improve the sample efficiency of reinforcement learning algorithms. In this work, we propose an approach to select and replay sequences of transitions in order to accelerate…

Artificial Intelligence · Computer Science 2022-09-29 Thommen George Karimpanal , Roland Bouffanais

Sample efficiency is a fundamental challenge in de novo molecular design. Ideally, molecular generative models should learn to satisfy a desired objective under minimal oracle evaluations (computational prediction or wet-lab experiment).…

Biomolecules · Quantitative Biology 2023-05-26 Jeff Guo , Philippe Schwaller

In this paper, we propose a novel technique, Back-stepping Experience Replay (BER), that is compatible with arbitrary off-policy reinforcement learning (RL) algorithms. BER aims to enhance learning efficiency in systems with approximate…

Robotics · Computer Science 2024-09-25 Xinda Qi , Dong Chen , Zhaojian Li , Xiaobo Tan

Jump stochastic volatility models are central to financial econometrics for volatility forecasting, portfolio risk management, and derivatives pricing. Markov Chain Monte Carlo (MCMC) algorithms are computationally unfeasible for the…

Applications · Statistics 2016-11-01 Eric Jacquier , Nicholas Polson , Vadim Sokolov

Hindsight Experience Replay (HER) is a multi-goal reinforcement learning algorithm for sparse reward functions. The algorithm treats every failure as a success for an alternative (virtual) goal that has been achieved in the episode. Virtual…

Machine Learning · Computer Science 2021-03-09 Binyamin Manela , Armin Biess

There is currently an increasing interest in large vector autoregressive (VAR) models. VARs are popular tools for macroeconomic forecasting and use of larger models has been demonstrated to often improve the forecasting ability compared to…

Econometrics · Economics 2019-07-03 Sebastian Ankargren , Paulina Jonéus

Missing modalities consistently lead to significant performance degradation in multimodal models. Existing approaches either synthesize missing modalities at high computational cost or apply prompt-based fine-tuning that relies only on…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Hongye Zhu , Xuan Liu , Yanwen Ba , Jingye Xue , Shigeng Zhang

Artificial neural networks are promising for general function approximation but challenging to train on non-independent or non-identically distributed data due to catastrophic forgetting. The experience replay buffer, a standard component…

Machine Learning · Computer Science 2023-04-12 Qingfeng Lan , Yangchen Pan , Jun Luo , A. Rupam Mahmood

We propose a very fast approximate Markov Chain Monte Carlo (MCMC) sampling framework that is applicable to a large class of sparse Bayesian inference problems, where the computational cost per iteration in several models is of order…

Computation · Statistics 2021-08-17 Yves Atchadé , Liwei Wang

Continual RL requires an agent to learn new tasks without forgetting previous ones, while improving on both past and future tasks. The most common approaches use model-free algorithms and replay buffers can help to mitigate catastrophic…

Machine Learning · Computer Science 2024-07-17 Luke Yang , Levin Kuhlmann , Gideon Kowadlo

Many real-world continuous control problems are in the dilemma of weighing the pros and cons, multi-objective reinforcement learning (MORL) serves as a generic framework of learning control policies for different preferences over…

Machine Learning · Computer Science 2024-07-26 Wei Hung , Bo-Kai Huang , Ping-Chun Hsieh , Xi Liu