English
Related papers

Related papers: MOTO: Offline Pre-training to Online Fine-tuning f…

200 papers

Offline-to-online reinforcement learning (RL) leverages both pre-trained offline policies and online policies trained for downstream tasks, aiming to improve data efficiency and accelerate performance enhancement. An existing approach,…

Machine Learning · Computer Science 2024-11-01 JaeYoon Kim , Junyu Xuan , Christy Liang , Farookh Hussain

Many real-world domains are subject to a structured non-stationarity which affects the agent's goals and the environmental dynamics. Meta-reinforcement learning (RL) has been shown successful for training agents that quickly adapt to…

Machine Learning · Computer Science 2021-05-20 Riccardo Poiani , Andrea Tirinzoni , Marcello Restelli

Through many recent successes in simulation, model-free reinforcement learning has emerged as a promising approach to solving continuous control robotic tasks. The research community is now able to reproduce, analyze and build quickly on…

Machine Learning · Computer Science 2018-09-21 A. Rupam Mahmood , Dmytro Korenkevych , Gautham Vasan , William Ma , James Bergstra

Offline reinforcement learning (RL) learns effective policies from pre-collected datasets, offering a practical solution for applications where online interactions are risky or costly. Model-based approaches are particularly advantageous…

Machine Learning · Computer Science 2026-05-14 Xuyang Chen , Keyu Yan , Guojian Wang , Lin Zhao

Online reinforcement learning is concerned with training an agent on-the-fly via dynamic interaction with the environment. Here, due to the specifics of the application, it is not generally possible to perform long pre-training, as it is…

Systems and Control · Electrical Eng. & Systems 2022-11-17 Grigory Yaremenko , Georgiy Malaniya , Pavel Osinenko

The appearance of transformer-based models in Reinforcement Learning (RL) has expanded the horizons of possibilities in robotics tasks, but it has simultaneously brought a wide range of challenges during its implementation, especially in…

Machine Learning · Computer Science 2025-10-01 Daniil Zelezetsky , Alexey K. Kovalev , Aleksandr I. Panov

Model-based offline reinforcement Learning (RL) is a promising approach that leverages existing data effectively in many real-world applications, especially those involving high-dimensional inputs like images and videos. To alleviate the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Shenghua Wan , Ziyuan Chen , Le Gan , Shuai Feng , De-Chuan Zhan

Fine-tuning is a widespread technique that allows practitioners to transfer pre-trained capabilities, as recently showcased by the successful applications of foundation models. However, fine-tuning reinforcement learning (RL) models remains…

The recent development of reinforcement learning (RL) has boosted the adoption of online RL for wireless radio resource management (RRM). However, online RL algorithms require direct interactions with the environment, which may be…

Information Theory · Computer Science 2023-11-21 Kun Yang , Cong Shen , Jing Yang , Shu-ping Yeh , Jerry Sydir

The modern paradigm in machine learning involves pre-training on diverse data, followed by task-specific fine-tuning. In reinforcement learning (RL), this translates to learning via offline RL on a diverse historical dataset, followed by…

Machine Learning · Computer Science 2025-07-03 Zhiyuan Zhou , Andy Peng , Qiyang Li , Sergey Levine , Aviral Kumar

In reinforcement learning (RL), an autonomous agent learns to perform complex tasks by maximizing an exogenous reward signal while interacting with its environment. In real-world applications, test conditions may differ substantially from…

Robotics · Computer Science 2019-10-30 Matteo Turchetta , Andreas Krause , Sebastian Trimpe

Vision-Language-Action (VLA) models have shown substantial potential in real-world robotic manipulation. However, fine-tuning these models through supervised learning struggles to achieve robust performance due to limited, inconsistent…

Robotics · Computer Science 2025-04-15 Yuhui Chen , Shuai Tian , Shugao Liu , Yingting Zhou , Haoran Li , Dongbin Zhao

Reinforcement learning from large-scale offline datasets provides us with the ability to learn policies without potentially unsafe or impractical exploration. Significant progress has been made in the past few years in dealing with the…

Machine Learning · Computer Science 2021-08-04 Philip J. Ball , Cong Lu , Jack Parker-Holder , Stephen Roberts

Connected and Automated Hybrid Electric Vehicles have the potential to reduce fuel consumption and travel time in real-world driving conditions. The eco-driving problem seeks to design optimal speed and power usage profiles based upon…

Machine Learning · Computer Science 2022-02-01 Zhaoxuan Zhu , Nicola Pivaro , Shobhit Gupta , Abhishek Gupta , Marcello Canova

Improving the performance of pre-trained policies through online reinforcement learning (RL) is a critical yet challenging topic. Existing online RL fine-tuning methods require continued training with offline pretrained Q-functions for…

Machine Learning · Computer Science 2025-05-23 Wei Xiao , Jiacheng Liu , Zifeng Zhuang , Runze Suo , Shangke Lyu , Donglin Wang

Offline reinforcement learning, which learns solely from datasets without environmental interaction, has gained attention. This approach, similar to traditional online deep reinforcement learning, is particularly promising for robot control…

Robotics · Computer Science 2025-07-21 Shingo Ayabe , Takuto Otomo , Hiroshi Kera , Kazuhiko Kawamoto

Among the reasons hindering reinforcement learning (RL) applications to real-world problems, two factors are critical: limited data and the mismatch between the testing environment (real environment in which the policy is deployed) and the…

Machine Learning · Computer Science 2023-01-30 Xiaoteng Ma , Zhipeng Liang , Jose Blanchet , Mingwen Liu , Li Xia , Jiheng Zhang , Qianchuan Zhao , Zhengyuan Zhou

How can we train a dialog model to produce better conversations by learning from human feedback, without the risk of humans teaching it harmful chat behaviors? We start by hosting models online, and gather human feedback from real-time,…

Developing agents that can execute multiple skills by learning from pre-collected datasets is an important problem in robotics, where online interaction with the environment is extremely time-consuming. Moreover, manually designing reward…

The training of autonomous agents often requires expensive and unsafe trial-and-error interactions with the environment. Nowadays several data sets containing recorded experiences of intelligent agents performing various tasks, spanning…

Machine Learning · Computer Science 2020-10-06 Giorgio Angelotti , Nicolas Drougard , Caroline Ponzoni Carvalho Chanel