English
Related papers

Related papers: World Models via Policy-Guided Trajectory Diffusio…

200 papers

Reinforcement Learning (RL) can effectively learn complex policies. However, learning these policies often demands extensive trial-and-error interactions with the environment. In many real-world scenarios, this approach is not practical due…

Machine Learning · Computer Science 2024-02-19 Linh Le Pham Van , Hung The Tran , Sunil Gupta

Cloth manipulation is challenging due to its highly complex dynamics, near-infinite degrees of freedom, and frequent self-occlusions, which complicate both state estimation and dynamics modeling. Inspired by recent advances in generative…

Robotics · Computer Science 2025-09-03 Tongxuan Tian , Haoyang Li , Bo Ai , Xiaodi Yuan , Zhiao Huang , Hao Su

Continuous-time long-term event prediction plays an important role in many application scenarios. Most existing works rely on autoregressive frameworks to predict event sequences, which suffer from error accumulation, thus compromising…

Machine Learning · Computer Science 2023-11-03 Wang-Tao Zhou , Zhao Kang , Ling Tian

Model-free reinforcement learning has emerged as a powerful method for developing robust robot control policies capable of navigating through complex and unstructured environments. The effectiveness of these methods hinges on two essential…

Robotics · Computer Science 2025-06-06 Youwei Yu , Junhong Xu , Lantao Liu

We study continual offline reinforcement learning, a practical paradigm that facilitates forward transfer and mitigates catastrophic forgetting to tackle sequential offline tasks. We propose a dual generative replay framework that retains…

Machine Learning · Computer Science 2024-04-19 Jinmei Liu , Wenbin Li , Xiangyu Yue , Shilin Zhang , Chunlin Chen , Zhi Wang

Decision Transformer (DT) can learn effective policy from offline datasets by converting the offline reinforcement learning (RL) into a supervised sequence modeling task, where the trajectory elements are generated auto-regressively…

Machine Learning · Computer Science 2024-11-19 Zhihong Liu , Long Qian , Zeyang Liu , Lipeng Wan , Xingyu Chen , Xuguang Lan

Diffusion models excel at creating images and videos thanks to their multimodal generative capabilities. These same capabilities have made diffusion models increasingly popular in robotics research, where they are used for generating robot…

Robotics · Computer Science 2025-04-29 Jean-Baptiste Bouvier , Kanghyun Ryu , Kartik Nagpal , Qiayuan Liao , Koushil Sreenath , Negar Mehr

Diffusion models have achieved remarkable success in sequential decision-making by leveraging the highly expressive model capabilities in policy learning. A central problem for learning diffusion policies is to align the policy output with…

Machine Learning · Computer Science 2024-12-17 Zhao Shan , Chenyou Fan , Shuang Qiu , Jiyuan Shi , Chenjia Bai

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties,…

Machine Learning · Computer Science 2020-10-16 Alekh Agarwal , Sham M. Kakade , Jason D. Lee , Gaurav Mahajan

Sequence-to-sequence architectures built upon recurrent neural networks have become a standard choice for multi-step-ahead time series prediction. In these models, the decoder produces future values conditioned on contextual inputs,…

Machine Learning · Computer Science 2026-02-06 Qi Sima , Xinze Zhang , Yukun Bao , Siyue Yang , Liang Shen

This paper develops the first policy gradient method with global optimality guarantee and complexity analysis for robust reinforcement learning under model mismatch. Robust reinforcement learning is to learn a policy robust to model…

Machine Learning · Computer Science 2022-05-17 Yue Wang , Shaofeng Zou

With the great success of diffusion models (DMs) in generating realistic synthetic vision data, many researchers have investigated their potential in decision-making and control. Most of these works utilized DMs to sample directly from the…

Machine Learning · Computer Science 2026-05-19 Hanye Zhao , Xiaoshen Han , Zhengbang Zhu , Minghuan Liu , Yong Yu , De-Chuan Zhan , Weinan Zhang

Classifier free guidance has shown strong potential in diffusion-based reinforcement learning. However, existing methods rely on joint training of the guidance module and the diffusion model, which can be suboptimal during the early stages…

Machine Learning · Computer Science 2025-06-05 Zhaoyang Chen , Cody Fleming

Offline reinforcement learning (RL) methods can generally be categorized into two types: RL-based and Imitation-based. RL-based methods could in principle enjoy out-of-distribution generalization but suffer from erroneous off-policy…

Machine Learning · Computer Science 2023-04-06 Haoran Xu , Li Jiang , Jianxiong Li , Xianyuan Zhan

Diffusion models have demonstrated empirical successes in various applications and can be adapted to task-specific needs via guidance. This paper studies a form of gradient guidance for adapting a pre-trained diffusion model towards…

Machine Learning · Statistics 2024-10-17 Yingqing Guo , Hui Yuan , Yukang Yang , Minshuo Chen , Mengdi Wang

We propose DemoDiffusion, a simple method for enabling robots to perform manipulation tasks by imitating a single human demonstration, without requiring task-specific training or paired human-robot data. Our approach is based on two…

Robotics · Computer Science 2026-03-10 Sungjae Park , Homanga Bharadhwaj , Shubham Tulsiani

Trajectory generation for mobile robots in unstructured environments faces a critical dilemma: balancing kinematic smoothness for safe execution with terminal precision for fine-grained tasks. Existing generative planners often struggle…

Robotics · Computer Science 2026-03-03 Jinyang Zhao , Handong Zheng , Yanjiu Zhong , Qiang Zhang , Yu Kang , Shunyu Wu

Mainstream visuomotor policies predominantly rely on generative models for holistic action prediction, while current autoregressive policies, predicting the next token or chunk, have shown suboptimal results. This motivates a search for…

Robotics · Computer Science 2025-03-18 Yue Su , Xinyu Zhan , Hongjie Fang , Han Xue , Hao-Shu Fang , Yong-Lu Li , Cewu Lu , Lixin Yang

End-to-end autonomous driving aims to generate safe and plausible planning policies from raw sensor input. Driving world models have shown great potential in learning rich representations by predicting the future evolution of a driving…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Xingtai Gui , Meijie Zhang , Tianyi Yan , Wencheng Han , Jiahao Gong , Feiyang Tan , Cheng-zhong Xu , Jianbing Shen

Imitation learning-based visuomotor policies excel at manipulation tasks but often produce suboptimal action trajectories compared to model-based methods. Directly mapping camera data to actions via neural networks can result in jerky…

Robotics · Computer Science 2025-11-11 Zhengtong Xu , Zichen Miao , Qiang Qiu , Zhe Zhang , Yu She