English
Related papers

Related papers: Decomposing the Prediction Problem; Autonomous Nav…

200 papers

Reinforcement Learning (RL) is a potent tool for sequential decision-making and has achieved performance surpassing human capabilities across many challenging real-world tasks. As the extension of RL in the multi-agent system domain,…

Artificial Intelligence · Computer Science 2024-08-20 Ruiqi Zhang , Jing Hou , Florian Walter , Shangding Gu , Jiayi Guan , Florian Röhrbein , Yali Du , Panpan Cai , Guang Chen , Alois Knoll

Visual navigation is a fundamental problem in embodied AI, yet practical deployments demand long-horizon planning capabilities to address multi-objective tasks. A major bottleneck is data scarcity: policies learned from limited data often…

Robotics · Computer Science 2025-10-22 Yiyuan Pan , Yunzhe Xu , Zhe Liu , Hesheng Wang

To navigate a space, the brain makes an internal representation of the environment using different cells such as place cells, grid cells, head direction cells, border cells, and speed cells. All these cells, along with sensory inputs,…

Robotics · Computer Science 2026-04-17 Hibatallah Meliani , Khadija Slimani , Samira Khoulji

The limited priors required by neural networks make them the dominating choice to encode and learn policies using reinforcement learning (RL). However, they are also black-boxes, making it hard to understand the agent's behaviour,…

Machine Learning · Computer Science 2023-10-26 Quentin Delfosse , Hikaru Shindo , Devendra Dhami , Kristian Kersting

The ultimate navigation efficiency of mobile robots in human environments will depend on how we will appraise them: merely as impersonal machines or as human-like agents. In the latter case, an agent may take advantage of the cooperative…

Vision-and-Language Navigation (VLN) tasks such as Room-to-Room (R2R) require machine agents to interpret natural language instructions and learn to act in visually realistic environments to achieve navigation goals. The overall task…

Computer Vision and Pattern Recognition · Computer Science 2019-08-14 Haoshuo Huang , Vihan Jain , Harsh Mehta , Alexander Ku , Gabriel Magalhaes , Jason Baldridge , Eugene Ie

In this work we use deep reinforcement learning to create an autonomous agent that can navigate in a two-dimensional space using only raw auditory sensory information from the environment, a problem that has received very little attention…

Sound · Computer Science 2021-05-17 Petros Giannakopoulos , Aggelos Pikrakis , Yannis Cotronis

Artificial neural systems trained using reinforcement, supervised, and unsupervised learning all acquire internal representations of high dimensional input. To what extent these representations depend on the different learning objectives is…

Neurons and Cognition · Quantitative Biology 2022-02-09 Grace W. Lindsay , Josh Merel , Tom Mrsic-Flogel , Maneesh Sahani

Autonomous AI is no longer a hard-to-reach concept, it enables the agents to move beyond executing tasks to independently addressing complex problems, adapting to change while handling the uncertainty of the environment. However, what makes…

Neurons and Cognition · Quantitative Biology 2025-05-12 Zinan Liu , Haoran Li , Jingyi Lu , Gaoyuan Ma , Xu Hong , Giovanni Iacca , Arvind Kumar , Shaojun Tang , Lin Wang

Embodied AI has been recently gaining attention as it aims to foster the development of autonomous and intelligent agents. In this paper, we devise a novel embodied setting in which an agent needs to explore a previously unknown environment…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Roberto Bigazzi , Federico Landi , Marcella Cornia , Silvia Cascianelli , Lorenzo Baraldi , Rita Cucchiara

"Embodied visual navigation" problem requires an agent to navigate in a 3D environment mainly rely on its first-person observation. This problem has attracted rising attention in recent years due to its wide application in autonomous…

Robotics · Computer Science 2021-10-12 Fengda Zhu , Yi Zhu , Vincent CS Lee , Xiaodan Liang , Xiaojun Chang

The hallmark of human intelligence is the self-evolving ability to master new skills by learning from past experiences. However, current AI agents struggle to emulate this self-evolution: fine-tuning is computationally expensive and prone…

Computation and Language · Computer Science 2026-02-13 Shengtao Zhang , Jiaqian Wang , Ruiwen Zhou , Junwei Liao , Yuchen Feng , Zhuo Li , Yujie Zheng , Weinan Zhang , Ying Wen , Zhiyu Li , Feiyu Xiong , Yutao Qi , Bo Tang , Muning Wen

Vision-Language Navigation (VLN) is a task where agents learn to navigate following natural language instructions. The key to this task is to perceive both the visual scene and natural language sequentially. Conventional approaches exploit…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Fengda Zhu , Yi Zhu , Xiaojun Chang , Xiaodan Liang

Embodied artificial intelligence (AI) tasks shift from tasks focusing on internet images to active settings involving embodied agents that perceive and act within 3D environments. In this paper, we investigate the target-driven visual…

Computer Vision and Pattern Recognition · Computer Science 2020-05-06 Yunlian Lv , Ning Xie , Yimin Shi , Zijiao Wang , Heng Tao Shen

We developed a simulated environment to train deep reinforcement learning agents on a shortcut usage navigation task, motivated by the Dual Solutions Paradigm test used for human navigators. We manipulated the frequency with which agents…

Machine Learning · Computer Science 2025-03-20 Andrew Liu , Alla Borisyuk

Many real-world reinforcement learning (RL) problems necessitate learning complex, temporally extended behavior that may only receive reward signal when the behavior is completed. If the reward-worthy behavior is known, it can be specified…

Machine Learning · Computer Science 2023-01-10 Phillip J. K. Christoffersen , Andrew C. Li , Rodrigo Toro Icarte , Sheila A. McIlraith

While computer vision models have made incredible strides in static image recognition, they still do not match human performance in tasks that require the understanding of complex, dynamic motion. This is notably true for real-world…

Neurons and Cognition · Quantitative Biology 2025-04-09 Jacob Yeung , Andrew F. Luo , Gabriel Sarch , Margaret M. Henderson , Deva Ramanan , Michael J. Tarr

The adaptive learning capabilities seen in biological neural networks are largely a product of the self-modifying behavior emerging from online plastic changes in synaptic connectivity. Current methods in Reinforcement Learning (RL) only…

Neural and Evolutionary Computing · Computer Science 2020-06-16 Samuel Schmidgall

Human error is a substantial factor in marine accidents, accounting for 85% of all reported incidents. By reducing the need for human intervention in vessel navigation, AI-based methods can potentially reduce the risk of accidents. AI…

Systems and Control · Electrical Eng. & Systems 2023-10-24 Joel Jose , Md Shadab Alam , Abhilash Sharma Somayajula

Navigation is crucial for animal behavior and is assumed to require an internal representation of the external environment, termed a cognitive map. The precise form of this representation is often considered to be a metric representation of…

Neurons and Cognition · Quantitative Biology 2020-02-10 Tie Xu , Omri Barak