English
Related papers

Related papers: Beyond Fine-Tuning: Transferring Behavior in Reinf…

200 papers

The ability for robots to transfer their learned knowledge to new tasks -- where data is scarce -- is a fundamental challenge for successful robot learning. While fine-tuning has been well-studied as a simple but effective transfer approach…

Robotics · Computer Science 2021-08-10 Zhangjie Cao , Minae Kwon , Dorsa Sadigh

Image-based reinforcement learning (RL) faces significant challenges in generalization when the visual environment undergoes substantial changes between training and deployment. Under such circumstances, learned policies may not perform…

Robotics · Computer Science 2024-07-25 Weiyao Wang , Xinyuan Fang , Gregory D. Hager

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…

In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which…

Machine Learning · Computer Science 2018-06-07 Xuhong Li , Yves Grandvalet , Franck Davoine

Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve this. However,…

Machine Learning · Computer Science 2023-02-17 Zhao Mandi , Pieter Abbeel , Stephen James

A crucial challenge in reinforcement learning is to reduce the number of interactions with the environment that an agent requires to master a given task. Transfer learning proposes to address this issue by re-using knowledge from previously…

Machine Learning · Computer Science 2023-04-28 Remo Sasso , Matthia Sabatelli , Marco A. Wiering

Behavior Trees (BTs) provide a structured and reactive framework for decision-making, commonly used to switch between sub-controllers based on environmental conditions. Reinforcement Learning (RL), on the other hand, can learn near-optimal…

Artificial Intelligence · Computer Science 2026-02-12 Finn Rietz , Mart Kartašev , Petter Ögren , Johannes A. Stork

There is growing evidence that pretrained language models improve task-specific fine-tuning not just for the languages seen in pretraining, but also for new languages and even non-linguistic data. What is the nature of this surprising…

Computation and Language · Computer Science 2021-04-20 Zhengxuan Wu , Nelson F. Liu , Christopher Potts

Transfer learning is beneficial by allowing the expressive features of models pretrained on large-scale datasets to be finetuned for the target task of smaller, more domain-specific datasets. However, there is a concern that these…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Angelina Wang , Olga Russakovsky

Reinforcement post training (RPT) has recently shown promise in improving the reasoning abilities of large language models (LLMs). However, it remains unclear how well these improvements generalize to new domains, as prior work evaluates…

Computation and Language · Computer Science 2026-03-03 Chuxuan Hu , Yuxuan Zhu , Antony Kellermann , Caleb Biddulph , Suppakit Waiwitlikhit , Jason Benn , Daniel Kang

Prior access to domain knowledge could significantly improve the performance of a reinforcement learning agent. In particular, it could help agents avoid potentially catastrophic exploratory actions, which would otherwise have to be…

Artificial Intelligence · Computer Science 2020-09-15 Thommen George Karimpanal , Santu Rana , Sunil Gupta , Truyen Tran , Svetha Venkatesh

Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize. We demonstrate that a trained agent fails completely when facing small visual changes, and that…

Computer Vision and Pattern Recognition · Computer Science 2019-07-05 Shani Gamrian , Yoav Goldberg

Reinforcement learning (RL) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs). However, LLMs can respond very inconsistently to RL finetuning: some show substantial…

Machine Learning · Computer Science 2025-10-07 Zhepeng Cen , Yihang Yao , William Han , Zuxin Liu , Ding Zhao

Reinforcement learning provides a general framework for flexible decision making and control, but requires extensive data collection for each new task that an agent needs to learn. In other machine learning fields, such as natural language…

Machine Learning · Computer Science 2020-11-20 Avi Singh , Huihan Liu , Gaoyue Zhou , Albert Yu , Nicholas Rhinehart , Sergey Levine

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

Transfer learning is a widely used method to build high performing computer vision models. In this paper, we study the efficacy of transfer learning by examining how the choice of data impacts performance. We find that more pre-training…

Computer Vision and Pattern Recognition · Computer Science 2018-12-13 Jiquan Ngiam , Daiyi Peng , Vijay Vasudevan , Simon Kornblith , Quoc V. Le , Ruoming Pang

Model-free reinforcement learning algorithms have exhibited great potential in solving single-task sequential decision-making problems with high-dimensional observations and long horizons, but are known to be hard to generalize across…

Machine Learning · Computer Science 2023-05-30 Boyuan Chen , Chuning Zhu , Pulkit Agrawal , Kaiqing Zhang , Abhishek Gupta

Pre-training and fine-tuning have achieved great success in the natural language process field. The standard paradigm of exploiting them includes two steps: first, pre-training a model, e.g. BERT, with a large scale unlabeled monolingual…

Computation and Language · Computer Science 2019-12-05 Rongxiang Weng , Heng Yu , Shujian Huang , Shanbo Cheng , Weihua Luo

Reinforcement learning is a learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in reinforcement learning upon the fast development of deep neural networks. Along with the…

Machine Learning · Computer Science 2023-07-06 Zhuangdi Zhu , Kaixiang Lin , Anil K. Jain , Jiayu Zhou

Evolutionary multitasking (EMT) algorithms typically require tailored designs for knowledge transfer, in order to assure convergence and optimality in multitask optimization. In this paper, we explore designing a systematic and…

Neural and Evolutionary Computing · Computer Science 2025-11-20 Jiajun Zhan , Zeyuan Ma , Yue-Jiao Gong , Kay Chen Tan
‹ Prev 1 2 3 10 Next ›