Learning Transferable Graph Exploration
This paper considers the problem of efficient exploration of unseen environments, a key challenge in AI. We propose a learning to explore' framework where we learn a policy from a distribution of environments. At test time, presented with an unseen environment from the same distribution, the policy aims to generalize the exploration strategy to visit the maximum number of unique states in a limited number of steps. We particularly focus on environments with graph-structured state-spaces that are encountered in many important real-world applications like software testing and map building. We formulate this task as a reinforcement learning problem where the exploration' agent is rewarded for transitioning to previously unseen environment states and employ a graph-structured memory to encode the agent's past trajectory. Experimental results demonstrate that our approach is extremely effective for exploration of spatial maps; and when applied on the challenging problems of coverage-guided software-testing of domain-specific programs and real-world mobile applications, it outperforms methods that have been hand-engineered by human experts.
Code (0)
등록된 구현이 없습니다.
Tasks
Efficient ExplorationReinforcement Learningsoftware testingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Zero-Shot Reinforcement Learning on Graphs for Autonomous Exploration Under Uncertainty
This paper studies the problem of autonomous exploration under localization uncertainty for a mobile robot with 3D range sensing. We present a framework for self-learning a high-performance exploration policy in a single…
Decision MakingDeep Reinforcement LearningDomain Adaptationreinforcement-learning+3Enabling ab initio geometry optimization of strongly correlated systems with transferable deep quantum Monte Carlo
A faithful description of chemical processes requires exploring extended regions of the molecular potential energy surface (PES), which remains challenging for strongly correlated systems. Transferable deep-learning vari…
Graph-Structured Gaussian Processes for Transferable Graph Learning
Transferable graph learning involves knowledge transferability from a source graph to a relevant target graph. The major challenge of transferable graph learning is the distribution shift between source and target graphs…
Open-World Distributed Robot Self-Localization with Transferable Visual Vocabulary and Both Absolute and Relative Features
Visual robot self-localization is a fundamental problem in visual robot navigation and has been studied across various problem settings, including monocular and sequential localization. However, many existing studies foc…
Graph Neural NetworkRobot NavigationA Comparative Study of Deep Reinforcement Learning-based Transferable Energy Management Strategies for Hybrid Electric Vehicles
The deep reinforcement learning-based energy management strategies (EMS) have become a promising solution for hybrid electric vehicles (HEVs). When driving cycles are changed, the neural network will be retrained, which …
Deep Reinforcement Learningenergy managementManagementreinforcement-learning+3