English
Related papers

Related papers: ED2: Environment Dynamics Decomposition World Mode…

200 papers

Reinforcement Learning (RL) has achieved impressive results in robotics, yet high-performing pipelines remain highly task-specific, with little reuse of prior data. Offline Model-based RL (MBRL) offers greater data efficiency by training…

Robotics · Computer Science 2026-01-09 Chenhao Li , Andreas Krause , Marco Hutter

Unsupervised Environment Design (UED) seeks to automatically generate training curricula for reinforcement learning (RL) agents, with the goal of improving generalisation and zero-shot performance. However, designing effective curricula…

Machine Learning · Computer Science 2026-01-22 Harry Mead , Bruno Lacerda , Jakob Foerster , Nick Hawes

Visual Model-Based Reinforcement Learning (MBRL) promises to encapsulate agent's knowledge about the underlying dynamics of the environment, enabling learning a world model as a useful planner. However, top MBRL agents such as Dreamer often…

Machine Learning · Computer Science 2024-05-31 Ruixiang Sun , Hongyu Zang , Xin Li , Riashat Islam

Reinforcement learning algorithms are typically designed for discrete-time dynamics, even though the underlying real-world control systems are often continuous in time. In this paper, we study the problem of continuous-time reinforcement…

Machine Learning · Computer Science 2026-03-03 Klemens Iten , Lenart Treven , Bhavya Sukhija , Florian Dörfler , Andreas Krause

Pretraining reinforcement learning (RL) models on offline datasets is a promising way to improve their training efficiency in online tasks, but challenging due to the inherent mismatch in dynamics and behaviors across various tasks. We…

Machine Learning · Computer Science 2024-06-06 Minting Pan , Yitao Zheng , Yunbo Wang , Xiaokang Yang

Balancing mutually diverging performance metrics, such as, processing latency, outcome accuracy, and end device energy consumption is a challenging undertaking for deep learning model inference in ad-hoc edge environments. In this paper, we…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-10-17 Motahare Mounesan , Xiaojie Zhang , Saptarshi Debroy

Visual model-based reinforcement learning (MBRL) agents can perform well on the training distribution, but often break down once the test environment shifts. In visual MBRL, recognizing that a shift has occurred is often the easier part;…

Machine Learning · Computer Science 2026-05-01 Haiyang Zhao

Diffusion world models have recently become competitive for online model-based reinforcement learning, but current approaches expose a tension: pixel diffusion is effective but computationally expensive while the latest latent diffusion…

Machine Learning · Computer Science 2026-05-14 Jing Yu Lim , Rushi Shah , Zarif Ikram , Samson Yu , Haozhe Ma , Tze-Yun Leong , Dianbo Liu

World models have recently emerged as a promising approach to reinforcement learning (RL), achieving state-of-the-art performance across a wide range of visual control tasks. This work aims to obtain a deep understanding of the robustness…

Machine Learning · Computer Science 2025-01-03 Qiaoyi Fang , Weiyu Du , Hang Wang , Junshan Zhang

Recent deep reinforcement learning (DRL) successes rely on end-to-end learning from fixed-size observational inputs (e.g. image, state-variables). However, many challenging and interesting problems in decision making involve observations or…

Machine Learning · Computer Science 2022-06-08 Vince Jankovics , Michael Garcia Ortiz , Eduardo Alonso

World model based reinforcement learning (RL) has emerged as a promising approach for autonomous driving, which learns a latent dynamics model and uses it to train a planning policy. To speed up the learning process, the pretrain-finetune…

Robotics · Computer Science 2025-01-24 Hang Wang , Xin Ye , Feng Tao , Chenbin Pan , Abhirup Mallik , Burhaneddin Yaman , Liu Ren , Junshan Zhang

Traditional linear control strategies have been extensively researched and utilized in many robotic and industrial applications and yet they do not respond to the total dynamics of the systems. To avoid tedious calculations for nonlinear…

Robotics · Computer Science 2022-03-16 Kanishk . , Rushil Kumar , Vikas Rastogi , Ajeet Kumar

In this paper, the problem of the trajectory design for a group of energy-constrained drones operating in dynamic wireless network environments is studied. In the considered model, a team of drone base stations (DBSs) is dispatched to…

Machine Learning · Computer Science 2020-12-08 Ye Hu , Mingzhe Chen , Walid Saad , H. Vincent Poor , Shuguang Cui

Efficient and effective learning is one of the ultimate goals of the deep reinforcement learning (DRL), although the compromise has been made in most of the time, especially for the application of robot manipulations. Learning is always…

Machine Learning · Computer Science 2020-03-06 Yongle Luo , Kun Dong , Lili Zhao , Zhiyong Sun , Chao Zhou , Bo Song

Dynamic resource allocation in mobile wireless networks involves complex, time-varying optimization problems, motivating the adoption of deep reinforcement learning (DRL). However, most existing works rely on pre-trained policies,…

Machine Learning · Computer Science 2025-02-12 Xinren Zhang , Jiadong Yu

Wireless networks are undergoing a paradigm shift toward massive connectivity with energy-efficient operation, driving the integration of satellite-terrestrial architectures with simultaneous wireless information and power transfer (SWIPT).…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-11 Guangyuan Liu , Yinqiu Liu , Ruichen Zhang , Dusit Niyato , Jiawen Kang , Sumei Sun , Abbas Jamalipour , Ping Zhang

The exponential proliferation of mobile devices and data-intensive applications in future wireless networks imposes substantial computational burdens on resource-constrained devices, thereby fostering the emergence of over-the-air…

Signal Processing · Electrical Eng. & Systems 2025-12-24 Tuo Wu , Xiazhi Lai , Shihang Lu , Zihao Chen , Xiaotong Zhao , Yuanhao Cui

Many consequential real-world systems, like wind fields and ocean currents, are dynamic and hard to model. Learning their governing dynamics remains a central challenge in scientific machine learning. Dynamic Mode Decomposition (DMD)…

Machine Learning · Computer Science 2025-11-26 Yujin Kim , Sarah Dean

Embed-to-control (E2C) is a model for solving high-dimensional optimal control problems by combining variational auto-encoders with locally-optimal controllers. However, the E2C model suffers from two major drawbacks: 1) its objective…

Machine Learning · Computer Science 2018-02-23 Ershad Banijamali , Rui Shu , Mohammad Ghavamzadeh , Hung Bui , Ali Ghodsi

Reinforcement learning (RL) has demonstrated potential for enhancing reasoning in large language models (LLMs). However, effective RL training, which requires medium-difficulty training samples, faces two fundamental challenges: Effective…

Machine Learning · Computer Science 2026-05-19 Ru Zhang , Renda Li , Ziyu Ma , Weijie Qiu , Chongyang Tao , Yong Wang , Xiangxiang Chu