English
Related papers

Related papers: BayRnTune: Adaptive Bayesian Domain Randomization …

200 papers

We propose a novel task-agnostic in-domain pre-training method that sits between generic pre-training and fine-tuning. Our approach selectively masks in-domain keywords, i.e., words that provide a compact representation of the target…

Computation and Language · Computer Science 2023-07-17 Shahriar Golchin , Mihai Surdeanu , Nazgol Tavabi , Ata Kiapour

Active policy search combines the trial-and-error methodology from policy search with Bayesian optimization to actively find the optimal policy. First, policy search is a type of reinforcement learning which has become very popular for…

Robotics · Computer Science 2024-02-13 Ruben Martinez-Cantin

In meta reinforcement learning (meta RL), an agent learns from a set of training tasks how to quickly solve a new task, drawn from the same task distribution. The optimal meta RL policy, a.k.a. the Bayes-optimal behavior, is well defined,…

Machine Learning · Computer Science 2024-04-01 Zohar Rimon , Aviv Tamar , Gilad Adler

Reinforcement learning encounters many challenges when applied directly in the real world. Sim-to-real transfer is widely used to transfer the knowledge learned from simulation to the real world. Domain randomization -- one of the most…

Machine Learning · Computer Science 2022-03-15 Xiaoyu Chen , Jiachen Hu , Chi Jin , Lihong Li , Liwei Wang

Robots are increasingly deployed in dynamic and crowded environments, such as urban areas and shopping malls, where efficient and robust navigation is crucial. Traditional risk-based motion planning algorithms face challenges in such…

Robotics · Computer Science 2024-11-04 Zhirui Sun , Bingyi Xia , Peijia Xie , Xiaoxiao Li , Jiankun Wang

A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. However, this assumption is violated in almost all practical applications: machine learning…

Machine Learning · Computer Science 2021-12-02 Marvin Zhang , Henrik Marklund , Nikita Dhawan , Abhishek Gupta , Sergey Levine , Chelsea Finn

We introduce a Bayesian (deep) model-based reinforcement learning method (RoMBRL) that can capture model uncertainty to achieve sample-efficient policy optimisation. We propose to formulate the model-based policy optimisation problem as a…

Robotics · Computer Science 2021-01-06 Tai Hoang , Ngo Anh Vien

In this work, we propose a novel variational Bayesian adaptive learning approach for cross-domain knowledge transfer to address acoustic mismatches between training and testing conditions, such as recording devices and environmental noise.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-28 Hu Hu , Sabato Marco Siniscalchi , Chao-Han Huck Yang , Chin-Hui Lee

Domain Adaptation (DA) methods are widely used in medical image segmentation tasks to tackle the problem of differently distributed train (source) and test (target) data. We consider the supervised DA task with a limited number of annotated…

Computer Vision and Pattern Recognition · Computer Science 2021-07-13 Ivan Zakazov , Boris Shirokikh , Alexey Chernyavskiy , Mikhail Belyaev

Despite ample motivation from costly exploration and limited trajectory data, rapidly adapting to new environments with few-shot reinforcement learning (RL) can remain a challenging task, especially with respect to personalized settings.…

Machine Learning · Computer Science 2020-10-13 Michael Zhang

Visual domain randomization in simulated environments is a widely used method to transfer policies trained in simulation to real robots. However, domain randomization and augmentation hamper the training of a policy. As reinforcement…

Machine Learning · Computer Science 2021-04-30 Artemij Amiranashvili , Max Argus , Lukas Hermann , Wolfram Burgard , Thomas Brox

Generalist robot manipulation policies (GMPs) have the potential to generalize across a wide range of tasks, devices, and environments. However, existing policies continue to struggle with out-of-distribution scenarios due to the inherent…

Robotics · Computer Science 2024-10-03 Wenbo Zhang , Yang Li , Yanyuan Qiao , Siyuan Huang , Jiajun Liu , Feras Dayoub , Xiao Ma , Lingqiao Liu

Reasoning has substantially improved the performance of large language models (LLMs) on complicated tasks. Central to the current reasoning studies, Process Reward Models (PRMs) offer a fine-grained evaluation of intermediate reasoning…

Machine Learning · Computer Science 2025-11-05 Qi Cao , Ruiyi Wang , Ruiyi Zhang , Sai Ashish Somayajula , Pengtao Xie

Reinforcement learning (RL) algorithms find applications in inventory control, recommender systems, vehicular traffic management, cloud computing and robotics. The real-world complications of many tasks arising in these domains makes them…

Machine Learning · Computer Science 2021-06-03 Sindhu Padakandla

In many real-world applications, we want to exploit multiple source datasets of similar tasks to learn a model for a different but related target dataset -- e.g., recognizing characters of a new font using a set of different fonts. While…

Machine Learning · Computer Science 2019-09-26 Junfeng Wen , Russell Greiner , Dale Schuurmans

Reinforcement Learning (RL) is a well-established framework for sequential decision-making in complex environments. However, state-of-the-art Deep RL (DRL) algorithms typically require large training datasets and often struggle to…

Artificial Intelligence · Computer Science 2026-04-13 Celeste Veronese , Alessandro Farinelli , Daniele Meli

Autonomous systems (AS) often use Deep Neural Network (DNN) classifiers to allow them to operate in complex, high-dimensional, non-linear, and dynamically changing environments. Due to the complexity of these environments, DNN classifiers…

Machine Learning · Computer Science 2024-08-16 Abanoub Ghobrial , Xuan Zheng , Darryl Hond , Hamid Asgari , Kerstin Eder

Randomize-then-optimize (RTO) is widely used for sampling from posterior distributions in Bayesian inverse problems. However, RTO may be computationally intensive for complexity problems due to repetitive evaluations of the expensive…

Numerical Analysis · Mathematics 2021-04-14 Liang Yan , Tao Zhou

We introduce an efficient and robust auto-tuning framework for hyperparameter selection in dimension reduction (DR) algorithms, focusing on large-scale datasets and arbitrary performance metrics. By leveraging Bayesian optimization (BO)…

Machine Learning · Statistics 2023-06-02 Yin-Ting Liao , Hengrui Luo , Anna Ma

Preference-based reinforcement learning (PbRL) aligns a robot behavior with human preferences via a reward function learned from binary feedback over agent behaviors. We show that dynamics-aware reward functions improve the sample…

Artificial Intelligence · Computer Science 2024-02-29 Katherine Metcalf , Miguel Sarabia , Natalie Mackraz , Barry-John Theobald