English
Related papers

Related papers: Sample-efficient Reinforcement Learning Representa…

200 papers

Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guided RL treat every new…

Machine Learning · Computer Science 2021-07-22 Karl Pertsch , Youngwoon Lee , Yue Wu , Joseph J. Lim

Current reinforcement learning algorithms train an agent using forward-generated trajectories, which provide little guidance so that the agent can explore as much as possible. While realizing the value of reinforcement learning results from…

Artificial Intelligence · Computer Science 2023-09-06 KyungMin Ko

Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but often at the cost of reduced output diversity. This trade-off between diversity and alignment…

Computation and Language · Computer Science 2025-06-03 Haoran Sun , Yekun Chai , Shuohuan Wang , Yu Sun , Hua Wu , Haifeng Wang

Despite recent advances in improving the sample-efficiency of reinforcement learning (RL) algorithms, designing an RL algorithm that can be practically deployed in real-world environments remains a challenge. In this paper, we present…

Robotics · Computer Science 2024-07-11 Younggyo Seo , Jafar Uruç , Stephen James

Continual learning has primarily focused on the issue of catastrophic forgetting and the associated stability-plasticity tradeoffs. However, little attention has been paid to the efficacy of continually learned representations, as…

Computer Vision and Pattern Recognition · Computer Science 2024-11-21 Ameya Prabhu , Shiven Sinha , Ponnurangam Kumaraguru , Philip H. S. Torr , Ozan Sener , Puneet K. Dokania

Structure learning of Conditional Random Fields (CRFs) can be cast into an L1-regularized optimization problem. To avoid optimizing over a fully linked model, gain-based or gradient-based feature selection methods start from an empty model…

Machine Learning · Computer Science 2014-07-01 Ni Lao , Jun Zhu

Recent multimodal models such as Contrastive Language-Image Pre-training (CLIP) have shown remarkable ability to align visual and linguistic representations. However, domains where small visual differences carry large semantic significance,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Hiroshi Sasaki

In Reinforcement Learning, the trade-off between exploration and exploitation poses a complex challenge for achieving efficient learning from limited samples. While recent works have been effective in leveraging past experiences for policy…

Machine Learning · Computer Science 2024-02-27 Nico Messikommer , Yunlong Song , Davide Scaramuzza

Model-free reinforcement learning has been successfully applied to a range of challenging problems, and has recently been extended to handle large neural network policies and value functions. However, the sample complexity of model-free…

Machine Learning · Computer Science 2016-03-03 Shixiang Gu , Timothy Lillicrap , Ilya Sutskever , Sergey Levine

Reinforcement learning (RL) can be used to tune data-driven (economic) nonlinear model predictive controllers ((e)NMPCs) for optimal performance in a specific control task by optimizing the dynamic model or parameters in the policy's…

Machine Learning · Computer Science 2025-05-14 Daniel Mayfrank , Mehmet Velioglu , Alexander Mitsos , Manuel Dahmen

Contrastive Learning (CL) has emerged as a powerful method for training feature extraction models using unlabeled data. Recent studies suggest that incorporating a linear projection head post-backbone significantly enhances model…

Machine Learning · Computer Science 2024-10-08 Huanran Li , Daniel Pimentel-Alarcón

We study the problem of Reinforcement Learning (RL) using as few real-world samples as possible. A naive application of RL can be inefficient in large and continuous state spaces. We present two versions of Multi-Fidelity Reinforcement…

Robotics · Computer Science 2020-03-10 Varun Suryan , Nahush Gondhalekar , Pratap Tokekar

Self-supervised contrastive learning is a powerful tool to learn visual representation without labels. Prior work has primarily focused on evaluating the recognition accuracy of various pre-training algorithms, but has overlooked other…

Computer Vision and Pattern Recognition · Computer Science 2022-06-13 Yuanyi Zhong , Haoran Tang , Junkun Chen , Jian Peng , Yu-Xiong Wang

Discovering what is learned by neural networks remains a challenge. In self-supervised learning, classification is the most common task used to evaluate how good a representation is. However, relying only on such downstream task can limit…

Machine Learning · Computer Science 2022-08-17 Florian Bordes , Randall Balestriero , Pascal Vincent

In this paper we present a world model, which learns causal features using the invariance principle. In particular, we use contrastive unsupervised learning to learn the invariant causal features, which enforces invariance across…

Machine Learning · Computer Science 2022-09-30 Rudra P. K. Poudel , Harit Pandya , Roberto Cipolla

Contrastive learning based on instance discrimination trains model to discriminate different transformations of the anchor sample from other samples, which does not consider the semantic similarity among samples. This paper proposes a new…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Hao Li , Xiaopeng Zhang , Hongkai Xiong

In visual Reinforcement Learning (RL), upstream representation learning largely determines the effect of downstream policy learning. Employing auxiliary tasks allows the agent to enhance visual representation in a targeted manner, thereby…

Machine Learning · Computer Science 2024-05-21 Xin Liu , Yaran Chen , Dongbin Zhao

Recent rehearsal-free continual learning (CL) methods guided by prompts achieve strong performance on vision tasks with non-stationary data but remain resource-intensive, hindering real-world edge deployment. We introduce resource-efficient…

Machine Learning · Computer Science 2025-12-17 Sungho Jeon , Xinyue Ma , Kwang In Kim , Myeongjae Jeon

Recently, self-supervised representation learning gives further development in multimedia technology. Most existing self-supervised learning methods are applicable to packaged data. However, when it comes to streamed data, they are…

Computer Vision and Pattern Recognition · Computer Science 2022-11-03 Zhiwei Lin , Yongtao Wang , Hongxiang Lin

Text embedding models play a crucial role in natural language processing, particularly in information retrieval, and their importance is further highlighted with the recent utilization of RAG (Retrieval- Augmented Generation). This study…

Information Retrieval · Computer Science 2024-12-24 Jeongsu Yu