English
Related papers

Related papers: Learning Transferable Graph Exploration

200 papers

Training robotic policies in simulation suffers from the sim-to-real gap, as simulated dynamics can be different from real-world dynamics. Past works tackled this problem through domain randomization and online system-identification. The…

Robotics · Computer Science 2020-11-09 Jacky Liang , Saumya Saxena , Oliver Kroemer

We address the task of long-horizon navigation in partially mapped environments for which active gathering of information about faraway unseen space is essential for good behavior. We present a novel planning strategy that, at training…

Robotics · Computer Science 2025-02-06 Raihan Islam Arnob , Gregory J. Stein

We consider a network scenario in which agents can evaluate each other according to a score graph that models some interactions. The goal is to design a distributed protocol, run by the agents, that allows them to learn their unknown state…

Systems and Control · Computer Science 2018-06-05 Francesco Sasso , Angelo Coluccia , Giuseppe Notarstefano

Reinforcement learning has empowered large language models to act as intelligent agents, yet training them for long-horizon tasks remains challenging due to the scarcity of high-quality trajectories, especially under limited resources.…

Machine Learning · Computer Science 2026-01-29 Jinyang Wu , Shuo Yang , Changpeng Yang , Yuhao Shen , Shuai Zhang , Zhengqi Wen , Jianhua Tao

Adaptive exploration methods propose ways to learn complex policies via alternating between exploration and exploitation. An important question for such methods is to determine the appropriate moment to switch between exploration and…

Artificial Intelligence · Computer Science 2026-02-11 Leonidas Bakopoulos , Georgios Chalkiadakis

We address planning and navigation in challenging 3D video games featuring maps with disconnected regions reachable by agents using special actions. In this setting, classical symbolic planners are not applicable or difficult to adapt. We…

Machine Learning · Computer Science 2021-12-23 Edward Beeching , Maxim Peter , Philippe Marcotte , Jilles Debangoye , Olivier Simonin , Joshua Romoff , Christian Wolf

Environments with controllable dynamics are usually understood in terms of explicit models. However, such models are not always available, but may sometimes be learned by exploring an environment. In this work, we investigate using an…

Machine Learning · Computer Science 2025-07-10 Peter N. Loxley , Friedrich T. Sommer

Tasks with large state space and sparse rewards present a longstanding challenge to reinforcement learning. In these tasks, an agent needs to explore the state space efficiently until it finds a reward. To deal with this problem, the…

Machine Learning · Computer Science 2023-10-16 Jiaheng Hu , Zizhao Wang , Peter Stone , Roberto Martin-Martin

We propose a hierarchical learning architecture for predictive control in unknown environments. We consider a constrained nonlinear dynamical system and assume the availability of state-input trajectories solving control tasks in different…

Systems and Control · Electrical Eng. & Systems 2020-07-16 Charlott Vallon , Francesco Borrelli

When deployed, AI agents will encounter problems that are beyond their autonomous problem-solving capabilities. Leveraging human assistance can help agents overcome their inherent limitations and robustly cope with unfamiliar situations. We…

Machine Learning · Computer Science 2022-06-24 Khanh Nguyen , Yonatan Bisk , Hal Daumé

Fast adapting to unknown peers (partners or opponents) with different strategies is a key challenge in multi-agent games. To do so, it is crucial for the agent to probe and identify the peer's strategy efficiently, as this is the…

Artificial Intelligence · Computer Science 2024-08-12 Long Ma , Yuanfei Wang , Fangwei Zhong , Song-Chun Zhu , Yizhou Wang

If a robotic agent wants to exploit symbolic planning techniques to achieve some goal, it must be able to properly ground an abstract planning domain in the environment in which it operates. However, if the environment is initially unknown…

Artificial Intelligence · Computer Science 2022-04-11 Leonardo Lamanna , Luciano Serafini , Alessandro Saetti , Alfonso Gerevini , Paolo Traverso

Understanding physical phenomena is a key component of human intelligence and enables physical interaction with previously unseen environments. In this paper, we study how an artificial agent can autonomously acquire this intuition through…

Robotics · Computer Science 2017-11-23 Wenbin Li , Jeannette Bohg , Mario Fritz

Modern cyber-physical systems are becoming increasingly complex to model, thus motivating data-driven techniques such as reinforcement learning (RL) to find appropriate control agents. However, most systems are subject to hard constraints…

This work addresses the problem of online exploration and visual sensor coverage of unknown environments. We introduce a novel perception roadmap we refer to as the Active Perception Network (APN) that serves as a hierarchical topological…

Robotics · Computer Science 2023-09-22 David Vutetakis , Jing Xiao

In this paper, we present an autonomous navigation system for goal-driven exploration of unknown environments through deep reinforcement learning (DRL). Points of interest (POI) for possible navigation directions are obtained from the…

Robotics · Computer Science 2021-09-10 Reinis Cimurs , Il Hong Suh , Jin Han Lee

We consider the exploration problem: an agent equipped with a depth sensor must map out a previously unknown environment using as few sensor measurements as possible. We propose an approach based on supervised learning of a greedy…

Machine Learning · Computer Science 2022-03-29 Louis Ly , Yen-Hsi Richard Tsai

Motivated by the increasing appeal of robots in information-gathering missions, we study multi-agent path planning problems in which the agents must remain interconnected. We model an area by a topological graph specifying the movement and…

Artificial Intelligence · Computer Science 2019-03-12 Tristan Charrier , Arthur Queffelec , Ocan Sankur , François Schwarzentruber

Existing grasp prediction approaches are mostly based on offline learning, while, ignoring the exploratory grasp learning during online adaptation to new picking scenarios, i.e., objects that are unseen or out-of-domain (OOD), camera and…

Planning - the ability to analyze the structure of a problem in the large and decompose it into interrelated subproblems - is a hallmark of human intelligence. While deep reinforcement learning (RL) has shown great promise for solving…

Artificial Intelligence · Computer Science 2021-07-02 Lunjun Zhang , Ge Yang , Bradly C. Stadie
‹ Prev 1 8 9 10 Next ›