Comparative Analysis of Loss Functions in TD3 forAutonomous Parking Article Swipe
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.30880/jscdm.2024.05.01.001
Autonomous parking is a revolutionary technology that has transformed the automotive industry with the rise of deep reinforcement learning, in particular, the Twin-Delayed Deep Deterministic Policy Gradient Algorithm (TD3). Nonetheless, the robustness of TD3 remains a significant challenge due to bias in Q-value estimates when determining how good an Action, A, taken at a particular state, S. To investigate this gap, this paper analyzes different loss functions in TD3 to better approximate the true Q-value, which is necessary for optimal decision making. Three loss functions are evaluated; Mean Squared Error (MSE), Mean Absolute Error (MAE) and Huber Loss via a simulation experiment for autonomous parking. The results showed that TD3 with Huber Loss has the highest convergence speed with the fastest Actor and Critic loss convergence. The Huber Loss function is found to be more robust and efficient than either loss function such MSE or MAE used in isolation, making it a suitable replacement for existing loss functions in the TD3 algorithm. In the future, TD3 with Huber Loss will be used as the base model to solve overestimation problem in TD3 when the estimated Q-values that represent the expected rewards of taking an action in a particular state, are higher than their true values.
Related Topics
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.30880/jscdm.2024.05.01.001
- OA Status
- diamond
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4403507353
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4403507353Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.30880/jscdm.2024.05.01.001Digital Object Identifier
- Title
-
Comparative Analysis of Loss Functions in TD3 forAutonomous ParkingWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-06-21Full publication date if available
- Authors
-
Ka Heng Chan, Aida Mustapha, Mohammed Ahmed JubairList of authors in order
- Landing page
-
https://doi.org/10.30880/jscdm.2024.05.01.001Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
diamondOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.30880/jscdm.2024.05.01.001Direct OA link when available
- Concepts
-
Transport engineering, EngineeringTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4403507353 |
|---|---|
| doi | https://doi.org/10.30880/jscdm.2024.05.01.001 |
| ids.doi | https://doi.org/10.30880/jscdm.2024.05.01.001 |
| ids.openalex | https://openalex.org/W4403507353 |
| fwci | 0.53997443 |
| type | article |
| title | Comparative Analysis of Loss Functions in TD3 forAutonomous Parking |
| biblio.issue | 1 |
| biblio.volume | 5 |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12546 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.9799000024795532 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2215 |
| topics[0].subfield.display_name | Building and Construction |
| topics[0].display_name | Smart Parking Systems Research |
| topics[1].id | https://openalex.org/T10761 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9549000263214111 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2208 |
| topics[1].subfield.display_name | Electrical and Electronic Engineering |
| topics[1].display_name | Vehicular Ad Hoc Networks (VANETs) |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C22212356 |
| concepts[0].level | 1 |
| concepts[0].score | 0.31690865755081177 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q775325 |
| concepts[0].display_name | Transport engineering |
| concepts[1].id | https://openalex.org/C127413603 |
| concepts[1].level | 0 |
| concepts[1].score | 0.2183929979801178 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[1].display_name | Engineering |
| keywords[0].id | https://openalex.org/keywords/transport-engineering |
| keywords[0].score | 0.31690865755081177 |
| keywords[0].display_name | Transport engineering |
| keywords[1].id | https://openalex.org/keywords/engineering |
| keywords[1].score | 0.2183929979801178 |
| keywords[1].display_name | Engineering |
| language | en |
| locations[0].id | doi:10.30880/jscdm.2024.05.01.001 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4210211867 |
| locations[0].source.issn | 2716-621X |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2716-621X |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Journal of Soft Computing and Data Mining |
| locations[0].source.host_organization | https://openalex.org/P4310322246 |
| locations[0].source.host_organization_name | Penerbit UTHM |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310322246 |
| locations[0].source.host_organization_lineage_names | Penerbit UTHM |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Journal of Soft Computing and Data Mining |
| locations[0].landing_page_url | https://doi.org/10.30880/jscdm.2024.05.01.001 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5062983141 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Ka Heng Chan |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Ka Heng Chan |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5032045434 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-9077-4995 |
| authorships[1].author.display_name | Aida Mustapha |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Aida Mustapha |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5107930857 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Mohammed Ahmed Jubair |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Mohammed Ahmed Jubair |
| authorships[2].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.30880/jscdm.2024.05.01.001 |
| open_access.oa_status | diamond |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-10-18T00:00:00 |
| display_name | Comparative Analysis of Loss Functions in TD3 forAutonomous Parking |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T12546 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.9799000024795532 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2215 |
| primary_topic.subfield.display_name | Building and Construction |
| primary_topic.display_name | Smart Parking Systems Research |
| related_works | https://openalex.org/W590383186, https://openalex.org/W1595912296, https://openalex.org/W567987265, https://openalex.org/W1596963112, https://openalex.org/W2362891875, https://openalex.org/W2290266725, https://openalex.org/W2406535223, https://openalex.org/W574715732, https://openalex.org/W11458981, https://openalex.org/W2742581101 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 1 |
| best_oa_location.id | doi:10.30880/jscdm.2024.05.01.001 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4210211867 |
| best_oa_location.source.issn | 2716-621X |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2716-621X |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Journal of Soft Computing and Data Mining |
| best_oa_location.source.host_organization | https://openalex.org/P4310322246 |
| best_oa_location.source.host_organization_name | Penerbit UTHM |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310322246 |
| best_oa_location.source.host_organization_lineage_names | Penerbit UTHM |
| best_oa_location.license | |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Journal of Soft Computing and Data Mining |
| best_oa_location.landing_page_url | https://doi.org/10.30880/jscdm.2024.05.01.001 |
| primary_location.id | doi:10.30880/jscdm.2024.05.01.001 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4210211867 |
| primary_location.source.issn | 2716-621X |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2716-621X |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Journal of Soft Computing and Data Mining |
| primary_location.source.host_organization | https://openalex.org/P4310322246 |
| primary_location.source.host_organization_name | Penerbit UTHM |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310322246 |
| primary_location.source.host_organization_lineage_names | Penerbit UTHM |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Journal of Soft Computing and Data Mining |
| primary_location.landing_page_url | https://doi.org/10.30880/jscdm.2024.05.01.001 |
| publication_date | 2024-06-21 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 3, 35, 53, 99, 151, 196 |
| abstract_inverted_index.A, | 50 |
| abstract_inverted_index.In | 162 |
| abstract_inverted_index.S. | 56 |
| abstract_inverted_index.To | 57 |
| abstract_inverted_index.an | 48, 193 |
| abstract_inverted_index.as | 172 |
| abstract_inverted_index.at | 52 |
| abstract_inverted_index.be | 133, 170 |
| abstract_inverted_index.in | 19, 41, 67, 147, 158, 180, 195 |
| abstract_inverted_index.is | 2, 76, 130 |
| abstract_inverted_index.it | 150 |
| abstract_inverted_index.of | 15, 32, 191 |
| abstract_inverted_index.or | 144 |
| abstract_inverted_index.to | 39, 69, 132, 176 |
| abstract_inverted_index.MAE | 145 |
| abstract_inverted_index.MSE | 143 |
| abstract_inverted_index.TD3 | 33, 68, 109, 160, 165, 181 |
| abstract_inverted_index.The | 105, 126 |
| abstract_inverted_index.and | 95, 122, 136 |
| abstract_inverted_index.are | 85, 199 |
| abstract_inverted_index.due | 38 |
| abstract_inverted_index.for | 78, 102, 154 |
| abstract_inverted_index.has | 7, 113 |
| abstract_inverted_index.how | 46 |
| abstract_inverted_index.the | 9, 13, 21, 30, 72, 114, 119, 159, 163, 173, 183, 188 |
| abstract_inverted_index.via | 98 |
| abstract_inverted_index.Deep | 23 |
| abstract_inverted_index.Loss | 97, 112, 128, 168 |
| abstract_inverted_index.Mean | 87, 91 |
| abstract_inverted_index.base | 174 |
| abstract_inverted_index.bias | 40 |
| abstract_inverted_index.deep | 16 |
| abstract_inverted_index.gap, | 60 |
| abstract_inverted_index.good | 47 |
| abstract_inverted_index.loss | 65, 83, 124, 140, 156 |
| abstract_inverted_index.more | 134 |
| abstract_inverted_index.rise | 14 |
| abstract_inverted_index.such | 142 |
| abstract_inverted_index.than | 138, 201 |
| abstract_inverted_index.that | 6, 108, 186 |
| abstract_inverted_index.this | 59, 61 |
| abstract_inverted_index.true | 73, 203 |
| abstract_inverted_index.used | 146, 171 |
| abstract_inverted_index.when | 44, 182 |
| abstract_inverted_index.will | 169 |
| abstract_inverted_index.with | 12, 110, 118, 166 |
| abstract_inverted_index.(MAE) | 94 |
| abstract_inverted_index.Actor | 121 |
| abstract_inverted_index.Error | 89, 93 |
| abstract_inverted_index.Huber | 96, 111, 127, 167 |
| abstract_inverted_index.Three | 82 |
| abstract_inverted_index.found | 131 |
| abstract_inverted_index.model | 175 |
| abstract_inverted_index.paper | 62 |
| abstract_inverted_index.solve | 177 |
| abstract_inverted_index.speed | 117 |
| abstract_inverted_index.taken | 51 |
| abstract_inverted_index.their | 202 |
| abstract_inverted_index.which | 75 |
| abstract_inverted_index.(MSE), | 90 |
| abstract_inverted_index.(TD3). | 28 |
| abstract_inverted_index.Critic | 123 |
| abstract_inverted_index.Policy | 25 |
| abstract_inverted_index.action | 194 |
| abstract_inverted_index.better | 70 |
| abstract_inverted_index.either | 139 |
| abstract_inverted_index.higher | 200 |
| abstract_inverted_index.making | 149 |
| abstract_inverted_index.robust | 135 |
| abstract_inverted_index.showed | 107 |
| abstract_inverted_index.state, | 55, 198 |
| abstract_inverted_index.taking | 192 |
| abstract_inverted_index.Action, | 49 |
| abstract_inverted_index.Q-value | 42 |
| abstract_inverted_index.Squared | 88 |
| abstract_inverted_index.fastest | 120 |
| abstract_inverted_index.future, | 164 |
| abstract_inverted_index.highest | 115 |
| abstract_inverted_index.making. | 81 |
| abstract_inverted_index.optimal | 79 |
| abstract_inverted_index.parking | 1 |
| abstract_inverted_index.problem | 179 |
| abstract_inverted_index.remains | 34 |
| abstract_inverted_index.results | 106 |
| abstract_inverted_index.rewards | 190 |
| abstract_inverted_index.values. | 204 |
| abstract_inverted_index.Absolute | 92 |
| abstract_inverted_index.Gradient | 26 |
| abstract_inverted_index.Q-value, | 74 |
| abstract_inverted_index.Q-values | 185 |
| abstract_inverted_index.analyzes | 63 |
| abstract_inverted_index.decision | 80 |
| abstract_inverted_index.existing | 155 |
| abstract_inverted_index.expected | 189 |
| abstract_inverted_index.function | 129, 141 |
| abstract_inverted_index.industry | 11 |
| abstract_inverted_index.parking. | 104 |
| abstract_inverted_index.suitable | 152 |
| abstract_inverted_index.Algorithm | 27 |
| abstract_inverted_index.challenge | 37 |
| abstract_inverted_index.different | 64 |
| abstract_inverted_index.efficient | 137 |
| abstract_inverted_index.estimated | 184 |
| abstract_inverted_index.estimates | 43 |
| abstract_inverted_index.functions | 66, 84, 157 |
| abstract_inverted_index.learning, | 18 |
| abstract_inverted_index.necessary | 77 |
| abstract_inverted_index.represent | 187 |
| abstract_inverted_index.Autonomous | 0 |
| abstract_inverted_index.algorithm. | 161 |
| abstract_inverted_index.automotive | 10 |
| abstract_inverted_index.autonomous | 103 |
| abstract_inverted_index.evaluated; | 86 |
| abstract_inverted_index.experiment | 101 |
| abstract_inverted_index.isolation, | 148 |
| abstract_inverted_index.particular | 54, 197 |
| abstract_inverted_index.robustness | 31 |
| abstract_inverted_index.simulation | 100 |
| abstract_inverted_index.technology | 5 |
| abstract_inverted_index.approximate | 71 |
| abstract_inverted_index.convergence | 116 |
| abstract_inverted_index.determining | 45 |
| abstract_inverted_index.investigate | 58 |
| abstract_inverted_index.particular, | 20 |
| abstract_inverted_index.replacement | 153 |
| abstract_inverted_index.significant | 36 |
| abstract_inverted_index.transformed | 8 |
| abstract_inverted_index.Nonetheless, | 29 |
| abstract_inverted_index.Twin-Delayed | 22 |
| abstract_inverted_index.convergence. | 125 |
| abstract_inverted_index.Deterministic | 24 |
| abstract_inverted_index.reinforcement | 17 |
| abstract_inverted_index.revolutionary | 4 |
| abstract_inverted_index.overestimation | 178 |
| cited_by_percentile_year.max | 95 |
| cited_by_percentile_year.min | 91 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile.value | 0.62310511 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |