English
Related papers

Related papers: STITCH-OPE: Trajectory Stitching with Guided Diffu…

200 papers

Research around Spiking Neural Networks has ignited during the last years due to their advantages when compared to traditional neural networks, including their efficient processing and inherent ability to model complex temporal dynamics.…

Neural and Evolutionary Computing · Computer Science 2022-10-04 Aitor Martinez Seras , Javier Del Ser , Jesus L. Lobo , Pablo Garcia-Bringas , Nikola Kasabov

Reasoning over long sequences of observations and actions is essential for many robotic tasks. Yet, learning effective long-context policies from demonstrations remains challenging. As context length increases, training becomes increasingly…

Robotics · Computer Science 2025-05-21 Marcel Torne , Andy Tang , Yuejiang Liu , Chelsea Finn

Existing offline hierarchical reinforcement learning methods rely on high-level policy learning to generate subgoal sequences. However, their efficiency degrades as task horizons increase, and they lack effective strategies for stitching…

Machine Learning · Computer Science 2025-07-08 Seungho Baek , Taegeon Park , Jongchan Park , Seungjun Oh , Yusung Kim

Offline reinforcement learning (RL) recovers the optimal policy $\pi$ given historical observations of an agent. In practice, $\pi$ is modeled as a weighted version of the agent's behavior policy $\mu$, using a weight function $w$ working…

Machine Learning · Computer Science 2025-12-24 Augusto Tagle , Javier Ruiz-del-Solar , Felipe Tobar

Discrete diffusion models have recently gained significant attention due to their ability to process complex discrete structures for language modeling. However, fine-tuning these models with policy gradient methods, as is commonly done in…

Machine Learning · Statistics 2025-12-19 Oussama Zekri , Nicolas Boullé

Stationary Distribution Correction Estimation (DICE) addresses the mismatch between the stationary distribution induced by a policy and the target distribution required for reliable off-policy evaluation (OPE) and policy optimization.…

Machine Learning · Computer Science 2025-06-11 Woosung Kim , JunHo Seo , Jongmin Lee , Byung-Jun Lee

Proximal Policy Optimization (PPO) is a popular model-free reinforcement learning algorithm, esteemed for its simplicity and efficacy. However, due to its inherent on-policy nature, its proficiency in harnessing data from disparate policies…

Machine Learning · Computer Science 2024-06-07 Yaozhong Gan , Renye Yan , Xiaoyang Tan , Zhe Wu , Junliang Xing

Spatiotemporal prediction over graphs (STPG) is challenging, because real-world data suffers from the Out-of-Distribution (OOD) generalization problem, where test data follow different distributions from training ones. To address this…

Machine Learning · Computer Science 2025-01-03 Zhaobin Mo , Haotian Xiang , Xuan Di

Diffusion-based policies have gained growing popularity in solving a wide range of decision-making tasks due to their superior expressiveness and controllable generation during inference. However, effectively training large diffusion…

Off-policy evaluation (OPE) aims to estimate the benefit of following a counterfactual sequence of actions, given data collected from executed sequences. However, existing OPE estimators often exhibit high bias and high variance in problems…

Machine Learning · Computer Science 2023-07-17 Aaman Rebello , Shengpu Tang , Jenna Wiens , Sonali Parbhoo

Offline reinforcement learning (RL) aims to learn the optimal policy from a fixed dataset generated by behavior policies without additional environment interactions. One common challenge that arises in this setting is the…

Machine Learning · Computer Science 2026-02-06 Songyuan Zhang , Oswin So , H. M. Sabbir Ahmad , Eric Yang Yu , Matthew Cleaveland , Mitchell Black , Chuchu Fan

Developing accurate off-policy estimators is crucial for both evaluating and optimizing for new policies. The main challenge in off-policy estimation is the distribution shift between the logging policy that generates data and the target…

Machine Learning · Computer Science 2023-10-25 Noveen Sachdeva , Lequn Wang , Dawen Liang , Nathan Kallus , Julian McAuley

Offline reinforcement learning (RL) is challenged by the distributional shift problem. To address this problem, existing works mainly focus on designing sophisticated policy constraints between the learned policy and the behavior policy.…

Machine Learning · Computer Science 2025-01-09 Yang Yue , Bingyi Kang , Xiao Ma , Qisen Yang , Gao Huang , Shiji Song , Shuicheng Yan

Out-of-distribution (OOD) detection is a crucial part of deploying machine learning models safely. It has been extensively studied with a plethora of methods developed in the literature. This problem is tackled with an OOD score…

Computer Vision and Pattern Recognition · Computer Science 2024-01-19 Jingqiu Zhou , Aojun Zhou , Hongsheng Li

Predicting counterfactual distributions in complex dynamical systems is essential for scientific modeling and decision-making in domains such as public health and medicine. However, existing methods often rely on point estimates or purely…

Machine Learning · Computer Science 2025-09-15 Wenhao Mu , Zhi Cao , Mehmed Uludag , Alexander Rodríguez

Offline reinforcement learning (RL) aims to learn optimal policies from previously collected datasets. Recently, due to their powerful representational capabilities, diffusion models have shown significant potential as policy models for…

Machine Learning · Computer Science 2024-05-30 Tianle Zhang , Jiayi Guan , Lin Zhao , Yihang Li , Dongjiang Li , Zecui Zeng , Lei Sun , Yue Chen , Xuelong Wei , Lusong Li , Xiaodong He

Diffusion-based inverse algorithms have shown remarkable performance across various inverse problems, yet their reliance on numerous denoising steps incurs high computational costs. While recent developments of fast diffusion ODE solvers…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Jiawei Zhang , Ziyuan Liu , Leon Yan , Gen Li , Yuantao Gu

The difficulty of exploring and training online on real production systems limits the scope of real-time online data/feedback-driven decision making. The most feasible approach is to adopt offline reinforcement learning from limited…

We study the problem of training diffusion models to sample from a distribution with a given unnormalized density or energy function. We benchmark several diffusion-structured inference methods, including simulation-based variational…

Offline multi-objective optimization aims to identify Pareto-optimal solutions given a dataset of designs and their objective values. In this work, we propose a preference-guided diffusion model that generates Pareto-optimal designs by…

Machine Learning · Computer Science 2025-12-19 Yashas Annadani , Syrine Belakaria , Stefano Ermon , Stefan Bauer , Barbara E Engelhardt