Value-based subgoal discovery and path planning for reaching long-horizon goals
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...
Saved in:
Main Authors: | Pateria, Shubham, Subagdja, Budhitama, Tan, Ah-Hwee, Quek, Chai |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/170579 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Value-based subgoal discovery and path planning for reaching long-horizon goals
by: PATERIA, Shubham, et al.
Published: (2023) -
End-to-end hierarchical reinforcement learning with integrated subgoal discovery
by: PATERIA, Shubham, et al.
Published: (2022) -
Hierarchical reinforcement learning with integrated discovery of salient subgoals
by: PATERIA, Shubham, et al.
Published: (2020) -
Interpretable goal recognition for path planning with ART networks
by: HU, Yue, et al.
Published: (2021) -
Motion planning under uncertainty for robotic tasks with long time horizons
by: Kurniawati, H., et al.
Published: (2013)