中文
相关论文

相关论文: Less is More: Clustered Cross-Covariance Control f…

200 篇论文

We consider the problem of offline reinforcement learning with model-based control, whose goal is to learn a dynamics model from the experience replay and obtain a pessimism-oriented agent under the learned model. Current model-based…

机器学习 · 计算机科学 2021-09-16 Ruizhen Liu , Dazhi Zhong , Zhicong Chen

Offline Reinforcement Learning (RL) enables policy optimization from static datasets but is inherently vulnerable to backdoor attacks. Existing attack strategies typically struggle against safety-constrained algorithms (e.g., CQL) due to…

机器学习 · 计算机科学 2026-01-16 Yuanjie Zhao , Junnan Qiu , Yue Ding , Jie Li

Distribution shifts between training and testing datasets significantly impair the model performance on graph learning. A commonly-taken causal view in graph invariant learning suggests that stable predictive features of graphs are causally…

机器学习 · 计算机科学 2025-12-10 Bohan Wang , Yurui Chang , Wei Jin , Lu Lin

Offline reinforcement learning (RL) heavily relies on the coverage of pre-collected data over the target policy's distribution. Existing studies aim to improve data-policy coverage to mitigate distributional shifts, but overlook security…

机器学习 · 计算机科学 2025-06-16 Xue Zhou , Dapeng Man , Chen Xu , Fanyi Zeng , Tao Liu , Huan Wang , Shucheng He , Chaoyang Gao , Wu Yang

The core challenge of offline reinforcement learning (RL) is dealing with the (potentially catastrophic) extrapolation error induced by the distribution shift between the history dataset and the desired policy. A large portion of prior work…

机器学习 · 计算机科学 2023-07-27 Laixi Shi , Robert Dadashi , Yuejie Chi , Pablo Samuel Castro , Matthieu Geist

Reinforcement learning (RL) has shown significant promise for sequential portfolio optimization tasks, such as stock trading, where the objective is to maximize cumulative returns while minimizing risks using historical data. However,…

机器学习 · 计算机科学 2025-05-20 Haochen Yuan , Minting Pan , Yunbo Wang , Siyu Gao , Philip S. Yu , Xiaokang Yang

The major challenge of offline RL is the distribution shift that appears when out-of-distribution actions are queried, which makes the policy improvement direction biased by extrapolation errors. Most existing methods address this problem…

机器学习 · 计算机科学 2024-02-29 Xiao Ma , Bingyi Kang , Zhongwen Xu , Min Lin , Shuicheng Yan

Off-policy learning ability is an important feature of reinforcement learning (RL) for practical applications. However, even one of the most elementary RL algorithms, temporal-difference (TD) learning, is known to suffer form divergence…

机器学习 · 计算机科学 2025-04-21 Han-Dong Lim , Donghwan Lee

The capability of continuously learning new skills via a sequence of pre-collected offline datasets is desired for an agent. However, consecutively learning a sequence of offline tasks likely leads to the catastrophic forgetting issue under…

机器学习 · 计算机科学 2024-04-23 Sibo Gai , Donglin Wang , Li He

Reinforcement Learning (RL) has been shown effective in domains where the agent can learn policies by actively interacting with its operating environment. However, if we change the RL scheme to offline setting where the agent can only…

机器学习 · 计算机科学 2021-11-11 Jinning Li , Chen Tang , Masayoshi Tomizuka , Wei Zhan

Offline reinforcement learning (RL) has garnered significant attention for its ability to learn effective policies from pre-collected datasets without the need for further environmental interactions. While promising results have been…

机器学习 · 计算机科学 2024-10-04 The Viet Bui , Thanh Hong Nguyen , Tien Mai

Offline Reinforcement Learning (RL) enables policy optimization from static datasets but is inherently vulnerable to data poisoning attacks. Existing attack strategies typically rely on locally uniform perturbations, which treat all samples…

机器学习 · 计算机科学 2025-12-11 Junnan Qiu , Yuanjie Zhao , Jie Li

Out-of-distribution (OoD) generalization occurs when representation learning encounters a distribution shift. This occurs frequently in practice when training and testing data come from different environments. Covariate shift is a type of…

机器学习 · 计算机科学 2026-04-22 Simon Zhang , Ryan P. DeMilt , Kun Jin , Cathy H. Xia

Offline reinforcement learning (RL) aims to learn decision policies from a fixed batch of logged transitions, without additional environment interaction. Despite remarkable empirical progress, offline RL remains fragile under distribution…

统计方法学 · 统计学 2026-03-16 Debashis Chatterjee

Offline reinforcement learning (RL) faces a significant challenge of distribution shift. Model-free offline RL penalizes the Q value for out-of-distribution (OOD) data or constrains the policy closed to the behavior policy to tackle this…

机器学习 · 计算机科学 2024-04-18 Xiao-Yin Liu , Xiao-Hu Zhou , Guotao Li , Hao Li , Mei-Jiang Gui , Tian-Yu Xiang , De-Xing Huang , Zeng-Guang Hou

Out-of-distribution (OOD) prediction remains a significant challenge in machine learning, particularly for tabular data where traditional methods often fail to generalize beyond their training distribution. This paper introduces Tabular…

机器学习 · 计算机科学 2025-05-21 Achmad Ginanjar , Xue Li , Priyanka Singh , Wen Hua

Offline reinforcement learning (RL) seeks to learn optimal policies from static datasets without further environment interaction. A key challenge is the distribution shift between the learned and behavior policies, leading to…

机器学习 · 计算机科学 2025-08-11 Haohui Chen , Zhiyong Chen

Offline reinforcement learning enables sample-efficient policy acquisition without risky online interaction, yet policies trained on static datasets remain brittle under action-space perturbations such as actuator faults. This study…

机器人学 · 计算机科学 2026-03-02 Shingo Ayabe , Hiroshi Kera , Kazuhiko Kawamoto

This paper concerns the central issues of model robustness and sample efficiency in offline reinforcement learning (RL), which aims to learn to perform decision making from history data without active exploration. Due to uncertainties and…

机器学习 · 计算机科学 2024-01-01 Laixi Shi , Yuejie Chi

For reliable deployment of deep-learning systems, out-of-distribution (OOD) detection is indispensable. In the real world, where test-time inputs often arrive as streaming mixtures of in-distribution (ID) and OOD samples under evolving…

计算机视觉与模式识别 · 计算机科学 2026-03-18 Wooseok Lee , Jin Mo Yang , Saewoong Bahk , Hyung-Sin Kim