English
Related papers

Related papers: Gated Memory Policy

200 papers

We present Masked Generative Policy (MGP), a novel framework for visuomotor imitation learning. We represent actions as discrete tokens, and train a conditional masked transformer that generates tokens in parallel and then rapidly refines…

Humanoid robots exhibit significant potential in executing diverse human-level skills. However, current research predominantly relies on data-driven approaches that necessitate extensive training datasets to achieve robust multimodal…

Robotics · Computer Science 2025-12-25 Xuetao Li , Wenke Huang , Nengyuan Pan , Kaiyan Zhao , Songhua Yang , Yiming Wang , Mengde Li , Mang Ye , Jifeng Xuan , Miao Li

Many manipulation tasks require memory beyond the current observation, yet most visuomotor policies rely on the Markov assumption and thus struggle with repeated states or long-horizon dependencies. Existing methods attempt to extend…

Robotics · Computer Science 2026-03-17 Jingjing Chen , Hongjie Fang , Chenxi Wang , Shiquan Wang , Cewu Lu

Imitation learning from human demonstrations has achieved significant success in robotic control, yet most visuomotor policies still condition on single-step observations or short-context histories, making them struggle with non-Markovian…

Robotics · Computer Science 2026-03-06 Yuheng Lei , Zhixuan Liang , Hongyuan Zhang , Ping Luo

Policy-gradient methods have received increased attention recently as a mechanism for learning to act in partially observable environments. They have shown promise for problems admitting memoryless policies but have been less successful…

Machine Learning · Computer Science 2025-12-08 Douglas Aberdeen , Jonathan Baxter

Memory is critical for long-horizon and history-dependent robotic manipulation. Such tasks often involve counting repeated actions or manipulating objects that become temporarily occluded. Recent vision-language-action (VLA) models have…

Robotics · Computer Science 2026-05-27 Yinpei Dai , Hongze Fu , Jayjun Lee , Yuejiang Liu , Haoran Zhang , Jianing Yang , Chelsea Finn , Nima Fazeli , Joyce Chai

Memory-augmented robotic policies are essential in handling memory-dependent tasks. However, existing approaches typically rely on simple observation window extensions, struggling to simultaneously achieve precise task state tracking and…

Robotics · Computer Science 2026-03-20 Liufan Tan , Jiale Li , Gangshan Jing

Generalist robot manipulation policies (GMPs) have the potential to generalize across a wide range of tasks, devices, and environments. However, existing policies continue to struggle with out-of-distribution scenarios due to the inherent…

Robotics · Computer Science 2024-10-03 Wenbo Zhang , Yang Li , Yanyuan Qiao , Siyuan Huang , Jiajun Liu , Feras Dayoub , Xiao Ma , Lingqiao Liu

Guided Policy Search enables robots to learn control policies for complex manipulation tasks efficiently. Therein, the control policies are represented as high-dimensional neural networks which derive robot actions based on states. However,…

Robotics · Computer Science 2019-02-20 Philipp Ennen , Pia Bresenitz , Rene Vossen , Frank Hees

Partially observable environments present an important open challenge in the domain of sequential control learning with delayed rewards. Despite numerous attempts during the two last decades, the majority of reinforcement learning…

Machine Learning · Statistics 2017-06-01 Julien Perez , Tomi Silander

It is of significance for an agent to learn a widely applicable and general-purpose policy that can achieve diverse goals including images and text descriptions. Considering such perceptually-specific goals, the frontier of deep…

Machine Learning · Computer Science 2021-12-14 Jinxin Liu , Donglin Wang , Qiangxing Tian , Zhengyu Chen

Optimal policies for partially observed Markov decision processes (POMDPs) are history-dependent: Decisions are made based on the entire history of observation. Memoryless policies, which take decisions based on the last observation only,…

Optimization and Control · Mathematics 2022-05-06 Victor Cohen , Axel Parmentier

Humanoid robot manipulation is a crucial research area for executing diverse human-level tasks, involving high-level semantic reasoning and low-level action generation. However, precise scene understanding and sample-efficient learning from…

Robotics · Computer Science 2026-01-15 Xuetao Li , Wenke Huang , Mang Ye , Jifeng Xuan , Bo Du , Sheng Liu , Miao Li

Despite the recent advancement in multi-agent reinforcement learning (MARL), the MARL agents easily overfit the training environment and perform poorly in the evaluation scenarios where other agents behave differently. Obtaining…

Multiagent Systems · Computer Science 2022-10-19 Wei Qiu , Xiao Ma , Bo An , Svetlana Obraztsova , Shuicheng Yan , Zhongwen Xu

Humans routinely rely on memory to perform tasks, yet most robot policies lack this capability; our goal is to endow robot policies with the same ability. Naively conditioning on long observation histories is computationally expensive and…

Robotics · Computer Science 2025-10-24 Ajay Sridhar , Jennifer Pan , Satvik Sharma , Chelsea Finn

Visuomotor policies trained via behavior cloning are vulnerable to covariate shift, where small deviations from expert trajectories can compound into failure. Common strategies to mitigate this issue involve expanding the training…

Robotics · Computer Science 2025-08-11 Zhanyi Sun , Shuran Song

Policy learning for partially observed control tasks requires policies that can remember salient information from past observations. In this paper, we present a method for learning policies with internal memory for high-dimensional,…

Machine Learning · Computer Science 2015-09-24 Marvin Zhang , Zoe McCarthy , Chelsea Finn , Sergey Levine , Pieter Abbeel

Humanoid whole-body loco-manipulation promises transformative capabilities for daily service and warehouse tasks. While recent advances in general motion tracking (GMT) have enabled humanoids to reproduce diverse human motions, these…

Robotics · Computer Science 2025-10-09 Siheng Zhao , Yanjie Ze , Yue Wang , C. Karen Liu , Pieter Abbeel , Guanya Shi , Rocky Duan

Planning plays an important role in the broad class of decision theory. Planning has drawn much attention in recent work in the robotics and sequential decision making areas. Recently, Reinforcement Learning (RL), as an agent-environment…

Artificial Intelligence · Computer Science 2016-08-18 Kamyar Azizzadenesheli , Alessandro Lazaric , Animashree Anandkumar

We present a fast and effective policy framework for robotic manipulation, named Energy Policy, designed for high-frequency robotic tasks and resource-constrained systems. Unlike existing robotic policies, Energy Policy natively predicts…

Robotics · Computer Science 2025-10-15 Jingkai Jia , Tong Yang , Xueyao Chen , Chenhuan Liu , Wenqiang Zhang
‹ Prev 1 2 3 10 Next ›