End-to-end hierarchical reinforcement learning with integrated subgoal discovery

Hierarchical reinforcement learning (HRL) is a promising approach to perform long-horizon goal-reaching tasks by decomposing the goals into subgoals. In a holistic HRL paradigm, an agent must autonomously discover such subgoals and also learn a hierarchy of policies that uses them to reach the goals...

Full description

Saved in:
Bibliographic Details
Main Authors: PATERIA, Shubham, SUBAGDJA, Budhitama, TAN, Ah-hwee, QUEK, Chai
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2022
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6416
https://ink.library.smu.edu.sg/context/sis_research/article/7419/viewcontent/End_to_End_Hierarchical_Reinforcement_Learning___IEEE_TNNLS_2021__Preprint_.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-7419
record_format dspace
spelling sg-smu-ink.sis_research-74192024-03-20T05:30:36Z End-to-end hierarchical reinforcement learning with integrated subgoal discovery PATERIA, Shubham SUBAGDJA, Budhitama TAN, Ah-hwee QUEK, Chai Hierarchical reinforcement learning (HRL) is a promising approach to perform long-horizon goal-reaching tasks by decomposing the goals into subgoals. In a holistic HRL paradigm, an agent must autonomously discover such subgoals and also learn a hierarchy of policies that uses them to reach the goals. Recently introduced end-to-end HRL methods accomplish this by using the higher-level policy in the hierarchy to directly search the useful subgoals in a continuous subgoal space. However, learning such a policy may be challenging when the subgoal space is large. We propose integrated discovery of salient subgoals (LIDOSS), an end-to-end HRL method with an integrated subgoal discovery heuristic that reduces the search space of the higher-level policy, by explicitly focusing on the subgoals that have a greater probability of occurrence on various state-transition trajectories leading to the goal. We evaluate LIDOSS on a set of continuous control tasks in the MuJoCo domain against hierarchical actor critic (HAC), a state-of-the-art end-to-end HRL method. The results show that LIDOSS attains better goal achievement rates than HAC in most of the tasks. 2022-12-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6416 info:doi/10.1109/TNNLS.2021.3087733 https://ink.library.smu.edu.sg/context/sis_research/article/7419/viewcontent/End_to_End_Hierarchical_Reinforcement_Learning___IEEE_TNNLS_2021__Preprint_.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Hierarchical reinforcement learning (HRL) reinforcement learning subgoal discovery task analysis Artificial Intelligence and Robotics Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Hierarchical reinforcement learning (HRL)
reinforcement learning
subgoal discovery
task analysis
Artificial Intelligence and Robotics
Databases and Information Systems
spellingShingle Hierarchical reinforcement learning (HRL)
reinforcement learning
subgoal discovery
task analysis
Artificial Intelligence and Robotics
Databases and Information Systems
PATERIA, Shubham
SUBAGDJA, Budhitama
TAN, Ah-hwee
QUEK, Chai
End-to-end hierarchical reinforcement learning with integrated subgoal discovery
description Hierarchical reinforcement learning (HRL) is a promising approach to perform long-horizon goal-reaching tasks by decomposing the goals into subgoals. In a holistic HRL paradigm, an agent must autonomously discover such subgoals and also learn a hierarchy of policies that uses them to reach the goals. Recently introduced end-to-end HRL methods accomplish this by using the higher-level policy in the hierarchy to directly search the useful subgoals in a continuous subgoal space. However, learning such a policy may be challenging when the subgoal space is large. We propose integrated discovery of salient subgoals (LIDOSS), an end-to-end HRL method with an integrated subgoal discovery heuristic that reduces the search space of the higher-level policy, by explicitly focusing on the subgoals that have a greater probability of occurrence on various state-transition trajectories leading to the goal. We evaluate LIDOSS on a set of continuous control tasks in the MuJoCo domain against hierarchical actor critic (HAC), a state-of-the-art end-to-end HRL method. The results show that LIDOSS attains better goal achievement rates than HAC in most of the tasks.
format text
author PATERIA, Shubham
SUBAGDJA, Budhitama
TAN, Ah-hwee
QUEK, Chai
author_facet PATERIA, Shubham
SUBAGDJA, Budhitama
TAN, Ah-hwee
QUEK, Chai
author_sort PATERIA, Shubham
title End-to-end hierarchical reinforcement learning with integrated subgoal discovery
title_short End-to-end hierarchical reinforcement learning with integrated subgoal discovery
title_full End-to-end hierarchical reinforcement learning with integrated subgoal discovery
title_fullStr End-to-end hierarchical reinforcement learning with integrated subgoal discovery
title_full_unstemmed End-to-end hierarchical reinforcement learning with integrated subgoal discovery
title_sort end-to-end hierarchical reinforcement learning with integrated subgoal discovery
publisher Institutional Knowledge at Singapore Management University
publishDate 2022
url https://ink.library.smu.edu.sg/sis_research/6416
https://ink.library.smu.edu.sg/context/sis_research/article/7419/viewcontent/End_to_End_Hierarchical_Reinforcement_Learning___IEEE_TNNLS_2021__Preprint_.pdf
_version_ 1794549873425514496