Please use this identifier to cite or link to this item:
|Title:||Value-based subgoal discovery and path planning for reaching long-horizon goals||Authors:||Pateria, Shubham
|Keywords:||Engineering::Computer science and engineering||Issue Date:||2023||Source:||Pateria, S., Subagdja, B., Tan, A. & Quek, C. (2023). Value-based subgoal discovery and path planning for reaching long-horizon goals. IEEE Transactions On Neural Networks and Learning Systems. https://dx.doi.org/10.1109/TNNLS.2023.3240004||Journal:||IEEE Transactions on Neural Networks and Learning Systems||Abstract:||Learning to reach long-horizon goals in spatial traversal tasks is a significant challenge for autonomous agents. Recent subgoal graph-based planning methods address this challenge by decomposing a goal into a sequence of shorter-horizon subgoals. These methods, however, use arbitrary heuristics for sampling or discovering subgoals, which may not conform to the cumulative reward distribution. Moreover, they are prone to learning erroneous connections (edges) between subgoals, especially those lying across obstacles. To address these issues, this article proposes a novel subgoal graph-based planning method called learning subgoal graph using value-based subgoal discovery and automatic pruning (LSGVP). The proposed method uses a subgoal discovery heuristic that is based on a cumulative reward (value) measure and yields sparse subgoals, including those lying on the higher cumulative reward paths. Moreover, LSGVP guides the agent to automatically prune the learned subgoal graph to remove the erroneous edges. The combination of these novel features helps the LSGVP agent to achieve higher cumulative positive rewards than other subgoal sampling or discovery heuristics, as well as higher goal-reaching success rates than other state-of-the-art subgoal graph-based planning methods.||URI:||https://hdl.handle.net/10356/170579||ISSN:||2162-237X||DOI:||10.1109/TNNLS.2023.3240004||Schools:||School of Computer Science and Engineering||Rights:||© 2023 IEEE. All rights reserved.||Fulltext Permission:||none||Fulltext Availability:||No Fulltext|
|Appears in Collections:||SCSE Journal Articles|
Updated on Dec 9, 2023
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.