English
Related papers

Related papers: Drift-Based Policy Optimization: Native One-Step P…

200 papers

The increasing complexity of tasks in robotics demands efficient strategies for multitask and continual learning. Traditional models typically rely on a universal policy for all tasks, facing challenges such as high computational costs and…

Modeling generalized robot control policies poses ongoing challenges for language-guided robot manipulation tasks. Existing methods often struggle to efficiently utilize cross-dataset resources or rely on resource-intensive vision-language…

Robotics · Computer Science 2024-11-05 Wenhui Tan , Bei Liu , Junbo Zhang , Ruihua Song , Jianlong Fu

Recent research on robot manipulation based on Behavior Cloning (BC) has made significant progress. By combining diffusion models with BC, diffusion policiy has been proposed, enabling robots to quickly learn manipulation tasks with high…

Robotics · Computer Science 2025-03-18 Qianhao Wang , Yinqian Sun , Enmeng Lu , Qian Zhang , Yi Zeng

Training reinforcement learning (RL) systems in real-world environments remains challenging due to noisy supervision and poor out-of-domain (OOD) generalization, especially in LLM post-training. Recent distributional RL methods improve…

Robust Markov decision processes (RMDPs) provide a promising framework for computing reliable policies in the face of model errors. Many successful reinforcement learning algorithms build on variations of policy-gradient methods, but…

Machine Learning · Computer Science 2024-05-15 Qiuhao Wang , Chin Pang Ho , Marek Petrik

Direct preference optimization (DPO) is a form of reinforcement learning from human feedback (RLHF) where the policy is learned directly from preferential feedback. Although many models of human preferences exist, the critical task of…

Machine Learning · Computer Science 2025-03-04 Branislav Kveton , Xintong Li , Julian McAuley , Ryan Rossi , Jingbo Shang , Junda Wu , Tong Yu

Developing a safe and efficient collision avoidance policy for multiple robots is challenging in the decentralized scenarios where each robot generate its paths without observing other robots' states and intents. While other distributed…

Robotics · Computer Science 2018-05-22 Pinxin Long , Tingxiang Fan , Xinyi Liao , Wenxi Liu , Hao Zhang , Jia Pan

We present an online model-based reinforcement learning algorithm suitable for controlling complex robotic systems directly in the real world. Unlike prevailing sim-to-real pipelines that rely on extensive offline simulation and model-free…

Robotics · Computer Science 2026-05-07 Fang Nan , Hao Ma , Qinghua Guan , Josie Hughes , Michael Muehlebach , Marco Hutter

We present a novel reinforcement learning method to train the quadruped robot in a simulated environment. The idea of controlling quadruped robots in a dynamic environment is quite challenging and my method presents the optimum policy and…

Robotics · Computer Science 2025-02-25 Nabeel Ahmad Khan Jadoon , Mongkol Ekpanyapong

Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such approaches fail to distinguish between high-value and low-value actions in their…

Many reinforcement learning (RL) tasks have discrete action spaces, but most generative policy methods based on diffusion and flow matching are designed for continuous control. Meanwhile, generative policies usually rely heavily on offline…

Machine Learning · Computer Science 2026-05-13 Fairoz Nower Khan , Nabuat Zaman Nahim , Peizhong Ju

Multi-robot navigation and path planning in continuous state and action spaces with uncertain environments remains an open challenge. Deep Reinforcement Learning (RL) is one of the most popular paradigms for solving this task, but its…

Robotics · Computer Science 2025-08-21 Jahid Chowdhury Choton , John Woods , William Hsu

Diffusion models have seen rapid adoption in robotic imitation learning, enabling autonomous execution of complex dexterous tasks. However, action synthesis is often slow, requiring many steps of iterative denoising, limiting the extent to…

Robotics · Computer Science 2024-10-14 Sigmund H. Høeg , Yilun Du , Olav Egeland

Diffusion Policy is a powerful technique tool for learning end-to-end visuomotor robot control. It is expected that Diffusion Policy possesses scalability, a key attribute for deep neural networks, typically suggesting that increasing model…

Limited by inference latency, existing robot manipulation policies lack sufficient real-time interaction capability with the environment. Although faster generation methods such as flow matching are gradually replacing diffusion methods,…

Robotics · Computer Science 2026-02-17 Zhenchen Dong , Jinna Fu , Jiaming Wu , Shengyuan Yu , Fulin Chen , Yide Liu

Generative models such as diffusion and flow-matching offer expressive policies for offline reinforcement learning (RL) by capturing rich, multimodal action distributions, but their iterative sampling introduces high inference costs and…

Machine Learning · Computer Science 2026-02-26 Prajwal Koirala , Cody Fleming

In offline reinforcement learning, value overestimation caused by out-of-distribution (OOD) actions significantly limits policy performance. Recently, diffusion models have been leveraged for their strong distribution-matching capabilities,…

Machine Learning · Computer Science 2025-11-13 Yunchang Ma , Tenglong Liu , Yixing Lan , Xin Yin , Changxin Zhang , Xinglong Zhang , Xin Xu

As single-center computing approaches power constraints, decentralized training becomes essential. However, traditional Reinforcement Learning (RL) methods, crucial for enhancing large model post-training, cannot adapt to decentralized…

Recently, Vision-Language-Action models (VLA) have advanced robot imitation learning, but high data collection costs and limited demonstrations hinder generalization and current imitation learning methods struggle in out-of-distribution…

Robotics · Computer Science 2026-02-24 Shichao Fan , Quantao Yang , Yajie Liu , Kun Wu , Zhengping Che , Qingjie Liu , Min Wan

Reinforcement learning (RL) has shown strong performance in LLM post-training, but real-world deployment often involves noisy or incomplete supervision. In such settings, complex and unreliable supervision signals can destabilize training…