English
Related papers

Related papers: Efficient transfer learning and online adaptation …

200 papers

Reinforcement learning (RL) policies trained in simulation often suffer from severe performance degradation when deployed in real-world environments due to non-stationary dynamics. While Domain Randomization (DR) and meta-RL have been…

Machine Learning · Computer Science 2026-02-09 Aoi Yoshimura , Gouhei Tanaka

Despite their effectiveness and popularity in offline or model-based reinforcement learning (RL), transformers remain underexplored in online model-free RL due to their sensitivity to training setups and model design decisions such as how…

Machine Learning · Computer Science 2025-10-16 Nikita Kachaev , Daniil Zelezetsky , Egor Cherepanov , Alexey K. Kovelev , Aleksandr I. Panov

To quickly solve new tasks in complex environments, intelligent agents need to build up reusable knowledge. For example, a learned world model captures knowledge about the environment that applies to new tasks. Similarly, skills capture…

Machine Learning · Computer Science 2021-05-04 Kevin Xie , Homanga Bharadhwaj , Danijar Hafner , Animesh Garg , Florian Shkurti

Although reinforcement learning methods can achieve impressive results in simulation, the real world presents two major challenges: generating samples is exceedingly expensive, and unexpected perturbations or unseen situations cause…

Machine Learning · Computer Science 2019-03-01 Anusha Nagabandi , Ignasi Clavera , Simin Liu , Ronald S. Fearing , Pieter Abbeel , Sergey Levine , Chelsea Finn

Online Reinforcement learning (RL) typically requires high-stakes online interaction data to learn a policy for a target task. This prompts interest in leveraging historical data to improve sample efficiency. The historical data may come…

Machine Learning · Computer Science 2024-11-07 Chengrui Qu , Laixi Shi , Kishan Panaganti , Pengcheng You , Adam Wierman

Reinforcement learning (RL) in robotics is often limited by the cost and risk of data collection, motivating experience transfer from a source task to a target task. Offline-to-online RL leverages prior data but typically assumes a given…

Machine Learning · Computer Science 2026-04-16 Mintae Kim , Koushil Sreenath

We consider the problem of estimating the transition dynamics $T^*$ from near-optimal expert trajectories in the context of offline model-based reinforcement learning. We develop a novel constraint-based method, Inverse Transition Learning,…

Machine Learning · Computer Science 2026-04-29 Leo Benac , Abhishek Sharma , Sonali Parbhoo , Finale Doshi-Velez

Reinforcement learning (RL) has demonstrated remarkable capability in acquiring robot skills, but learning each new skill still requires substantial data collection for training. The pretrain-and-finetune paradigm offers a promising…

Robotics · Computer Science 2025-03-25 Ziang Zheng , Guojian Zhan , Bin Shuai , Shengtao Qin , Jiangtao Li , Tao Zhang , Shengbo Eben Li

Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL). This paper expands the pool of usable data for offline-to-online RL by leveraging abundant non-curated data that is…

Machine Learning · Computer Science 2025-05-20 Yi Zhao , Aidan Scannell , Wenshuai Zhao , Yuxin Hou , Tianyu Cui , Le Chen , Dieter Büchler , Arno Solin , Juho Kannala , Joni Pajarinen

Reinforcement learning (RL) is widely used in autonomous driving tasks and training RL models typically involves in a multi-step process: pre-training RL models on simulators, uploading the pre-trained model to real-life robots, and…

Machine Learning · Computer Science 2019-10-15 Xinle Liang , Yang Liu , Tianjian Chen , Ming Liu , Qiang Yang

Learning-based control methods typically assume stationary system dynamics, an assumption often violated in real-world systems due to drift, wear, or changing operating conditions. We study reinforcement learning for control under…

Machine Learning · Computer Science 2026-04-03 Klemens Iten , Bruce Lee , Chenhao Li , Lenart Treven , Andreas Krause , Bhavya Sukhija

Model-based reinforcement learning could enable sample-efficient learning by quickly acquiring rich knowledge about the world and using it to improve behaviour without additional data. Learned dynamics models can be directly used for…

Machine Learning · Computer Science 2019-10-15 Rinu Boney , Juho Kannala , Alexander Ilin

Offline reinforcement learning (RL) allows learning sequential behavior from fixed datasets. Since offline datasets do not cover all possible situations, many methods collect additional data during online fine-tuning to improve performance.…

Machine Learning · Computer Science 2024-06-13 Mohammadreza Nakhaei , Aidan Scannell , Joni Pajarinen

Reinforcement learning (RL) has been used in a range of simulated real-world tasks, e.g., sensor coordination, traffic light control, and on-demand mobility services. However, real world deployments are rare, as RL struggles with dynamic…

Machine Learning · Computer Science 2021-12-02 Alberto Castagna , Ivana Dusparic

Model-based reinforcement learning (RL) is anticipated to exhibit higher sample efficiency compared to model-free RL by utilizing a virtual environment model. However, it is challenging to obtain sufficiently accurate representations of the…

Artificial Intelligence · Computer Science 2026-01-19 Zihao Sheng , Zilin Huang , Sikai Chen

Transfer learning is a machine learning paradigm where knowledge from one problem is utilized to solve a new but related problem. While conceivable that knowledge from one task could be useful for solving a related task, if not executed…

Machine Learning · Computer Science 2021-10-01 Xuetong Wu , Jonathan H. Manton , Uwe Aickelin , Jingge Zhu

A central capability of a long-lived reinforcement learning (RL) agent is to incrementally adapt its behavior as its environment changes, and to incrementally build upon previous experiences to facilitate future learning in real-world…

Machine Learning · Computer Science 2021-02-15 Zhi Wang , Chunlin Chen , Daoyi Dong

Offline meta-reinforcement learning seeks to learn policies that generalize across related tasks from fixed datasets. Context-based methods infer a task representation from transition histories, but learning effective task representations…

Machine Learning · Computer Science 2026-03-04 Mohammadreza Nakheai , Aidan Scannell , Kevin Luck , Joni Pajarinen

We consider a semi-supervised classification problem with non-stationary label-shift in which we observe a labelled data set followed by a sequence of unlabelled covariate vectors in which the marginal probabilities of the class labels may…

Statistics Theory · Mathematics 2024-05-29 Henry W J Reeve

Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed for online learning struggle in the offline setting as they…

Machine Learning · Computer Science 2025-03-18 Natinael Solomon Neggatu , Jeremie Houssineau , Giovanni Montana