中文
相关论文

相关论文: World Model as a Graph: Learning Latent Landmarks …

200 篇论文

Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert…

机器人学 · 计算机科学 2025-04-24 Amber Xie , Oleh Rybkin , Dorsa Sadigh , Chelsea Finn

In this paper, we propose a novel Deep Reinforcement Learning approach to address the mapless navigation problem, in which the locomotion actions of a humanoid robot are taken online based on the knowledge encoded in learned models.…

机器人学 · 计算机科学 2021-08-10 Andre Brandenburger , Diego Rodriguez , Sven Behnke

We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable for probabilistic planning at multiple levels of abstraction. We call this framework Planning with…

Deep reinforcement learning (DRL) methods have recently shown promise in path planning tasks. However, when dealing with global planning tasks, these methods face serious challenges such as poor convergence and generalization. To this end,…

机器学习 · 计算机科学 2024-01-10 Guoming Huang , Mingxin Hou , Xiaofang Yuan , Shuqiao Huang , Yaonan Wang

Can large language models (LLMs) directly serve as powerful world models for model-based agents? While the gaps between the prior knowledge of LLMs and the specified environment's dynamics do exist, our study reveals that the gaps can be…

人工智能 · 计算机科学 2024-10-15 Siyu Zhou , Tianyi Zhou , Yijun Yang , Guodong Long , Deheng Ye , Jing Jiang , Chengqi Zhang

Planning with a learned model is arguably a key component of intelligence. There are several challenges in realizing such a component in large-scale reinforcement learning (RL) problems. One such challenge is dealing effectively with…

机器学习 · 计算机科学 2022-02-11 Vivek Veeriah , Zeyu Zheng , Richard Lewis , Satinder Singh

Recently, graph-based planning algorithms have gained much attention to solve goal-conditioned reinforcement learning (RL) tasks: they provide a sequence of subgoals to reach the target-goal, and the agents learn to execute…

机器学习 · 计算机科学 2023-03-21 Junsu Kim , Younggyo Seo , Sungsoo Ahn , Kyunghwan Son , Jinwoo Shin

Model-free reinforcement learning algorithms have exhibited great potential in solving single-task sequential decision-making problems with high-dimensional observations and long horizons, but are known to be hard to generalize across…

机器学习 · 计算机科学 2023-05-30 Boyuan Chen , Chuning Zhu , Pulkit Agrawal , Kaiqing Zhang , Abhishek Gupta

Efficient job allocation in complex scheduling problems poses significant challenges in real-world applications. In this report, we propose a novel approach that leverages the power of Reinforcement Learning (RL) and Graph Neural Networks…

机器学习 · 计算机科学 2025-02-03 Lars C. P. M. Quaedvlieg

To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it to the task at hand. Recent advances in representation…

Developing foundational world models is a key research direction for embodied intelligence, with the ability to adapt to non-stationary environments being a crucial criterion. In this work, we introduce a new formalism, Hidden…

机器学习 · 计算机科学 2024-11-05 Emiliyan Gospodinov , Vaisakh Shaj , Philipp Becker , Stefan Geyer , Gerhard Neumann

The navigation problem is classically approached in two steps: an exploration step, where map-information about the environment is gathered; and an exploitation step, where this information is used to navigate efficiently. Deep…

机器人学 · 计算机科学 2019-01-08 Vikas Dhiman , Shurjo Banerjee , Brent Griffin , Jeffrey M Siskind , Jason J Corso

To achieve autonomy in a priori unknown real-world scenarios, agents should be able to: i) act from high-dimensional sensory observations (e.g., images), ii) learn from past experience to adapt and improve, and iii) be capable of long…

机器人学 · 计算机科学 2022-12-12 Onur Beker , Mohammad Mohammadi , Amir Zamir

Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural Networks (DNNs) for function approximation, has demonstrated considerable success in numerous applications. However, its practicality in addressing various…

机器学习 · 计算机科学 2024-04-26 Aditya Mohan , Amy Zhang , Marius Lindauer

Route planning is important in transportation. Existing works focus on finding the shortest path solution or using metrics such as safety and energy consumption to determine the planning. It is noted that most of these studies rely on prior…

机器学习 · 计算机科学 2020-11-06 Yuanzhe Geng , Erwu Liu , Rui Wang , Yiming Liu

Data-efficient learning remains a central challenge in autonomous driving due to the high cost and safety risks of large-scale real-world interaction. Although world-model-based reinforcement learning enables policy optimization through…

机器人学 · 计算机科学 2026-03-10 Jiazhuo Li , Linjiang Cao , Qi Liu , Xi Xiong

We present a relational graph learning approach for robotic crowd navigation using model-based deep reinforcement learning that plans actions by looking into the future. Our approach reasons about the relations between all agents based on…

机器人学 · 计算机科学 2020-08-05 Changan Chen , Sha Hu , Payam Nikdel , Greg Mori , Manolis Savva

Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning. However, challenges remain under-explored for parallel schedules. This paper introduces a novel paradigm, plan-over-graph, in which the…

人工智能 · 计算机科学 2025-02-21 Shiqi Zhang , Xinbei Ma , Zouying Cao , Zhuosheng Zhang , Hai Zhao

Autonomous mobile robots operating in complex, dynamic environments face the dual challenge of navigating large-scale, structurally diverse spaces with static obstacles while safely interacting with various moving agents. Traditional…

机器人学 · 计算机科学 2026-01-01 Yury Kolomeytsev , Dmitry Golembiovsky

Graph neural networks (GNNs) have emerged as the standard method for numerous tasks on graph-structured data such as node classification. However, real-world graphs are often evolving over time and even new classes may arise. We model these…

机器学习 · 计算机科学 2021-12-21 Lukas Galke , Benedikt Franke , Tobias Zielke , Ansgar Scherp