Changes

              
    

          
          
        
        

            
f
1
{
f
1
{
            
2
  "access_rights": "",
2
  "access_rights": "",
            
3
  "author": "Yuguang Yang",
3
  "author": "Yuguang Yang",
            
4
  "author_email": "",
4
  "author_email": "",
            
5
  "citation": [],
5
  "citation": [],
            
6
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
6
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            
7
  "defined_in": "https://doi.org/10.48550/arXiv.1911.10684",
7
  "defined_in": "https://doi.org/10.48550/arXiv.1911.10684",
            
8
  "doi": "10.57702/y6obe121",
8
  "doi": "10.57702/y6obe121",
            
n
9
  "doi_date_published": null,
n
9
  "doi_date_published": "2024-12-16",
            
10
  "doi_publisher": "TIB",
10
  "doi_publisher": "TIB",
            
n
11
  "doi_status": false,
n
11
  "doi_status": true,
            
12
  "domain": "https://service.tib.eu/ldmservice",
12
  "domain": "https://service.tib.eu/ldmservice",
            
13
  "extra_authors": [
13
  "extra_authors": [
            
14
    {
14
    {
            
15
      "extra_author": "Johns Hopkins University",
15
      "extra_author": "Johns Hopkins University",
            
16
      "orcid": ""
16
      "orcid": ""
            
17
    }
17
    }
            
18
  ],
18
  ],
            
19
  "groups": [
19
  "groups": [
            
20
    {
20
    {
            
21
      "description": "",
21
      "description": "",
            
22
      "display_name": "Deep Reinforcement Learning",
22
      "display_name": "Deep Reinforcement Learning",
            
23
      "id": "5a11e7f6-fbd8-4990-a7f6-dc1c77b11c75",
23
      "id": "5a11e7f6-fbd8-4990-a7f6-dc1c77b11c75",
            
24
      "image_display_url": "",
24
      "image_display_url": "",
            
25
      "name": "deep-reinforcement-learning",
25
      "name": "deep-reinforcement-learning",
            
26
      "title": "Deep Reinforcement Learning"
26
      "title": "Deep Reinforcement Learning"
            
27
    },
27
    },
            
28
    {
28
    {
            
29
      "description": "",
29
      "description": "",
            
30
      "display_name": "Multi-stage Optimal Control",
30
      "display_name": "Multi-stage Optimal Control",
            
31
      "id": "0b2fc919-ece7-472c-af2f-5dc853687f6b",
31
      "id": "0b2fc919-ece7-472c-af2f-5dc853687f6b",
            
32
      "image_display_url": "",
32
      "image_display_url": "",
            
33
      "name": "multi-stage-optimal-control",
33
      "name": "multi-stage-optimal-control",
            
34
      "title": "Multi-stage Optimal Control"
34
      "title": "Multi-stage Optimal Control"
            
35
    }
35
    }
            
36
  ],
36
  ],
            
37
  "id": "fc3f9733-b49e-4d77-b0ca-8e2c1e064b75",
37
  "id": "fc3f9733-b49e-4d77-b0ca-8e2c1e064b75",
            
38
  "isopen": false,
38
  "isopen": false,
            
39
  "landing_page": "",
39
  "landing_page": "",
            
40
  "license_title": null,
40
  "license_title": null,
            
41
  "link_orkg": "",
41
  "link_orkg": "",
            
42
  "metadata_created": "2024-12-16T23:09:28.686291",
42
  "metadata_created": "2024-12-16T23:09:28.686291",
            
n
43
  "metadata_modified": "2024-12-16T23:09:28.686297",
n
43
  "metadata_modified": "2024-12-16T23:09:29.271076",
            
44
  "name": 
44
  "name": 
            
45
-reinforcement-learning-architecture-for-multi-stage-optimal-control",
45
-reinforcement-learning-architecture-for-multi-stage-optimal-control",
            
46
  "notes": "Deep reinforcement learning for high dimensional, 
46
  "notes": "Deep reinforcement learning for high dimensional, 
            
47
hierarchical control tasks usually requires the use of complex neural 
47
hierarchical control tasks usually requires the use of complex neural 
            
48
networks as functional approximators, which can lead to 
48
networks as functional approximators, which can lead to 
            
49
inef\ufb01ciency, instability and even divergence in the training 
49
inef\ufb01ciency, instability and even divergence in the training 
            
50
process. Here, we introduce stacked deep Q learning (SDQL), a 
50
process. Here, we introduce stacked deep Q learning (SDQL), a 
            
51
\ufb02exible modularized deep reinforcement learning architecture, 
51
\ufb02exible modularized deep reinforcement learning architecture, 
            
52
that can enable \ufb01nding of optimal control policy of control tasks 
52
that can enable \ufb01nding of optimal control policy of control tasks 
            
53
consisting of multiple linear stages in a stable and ef\ufb01cient 
53
consisting of multiple linear stages in a stable and ef\ufb01cient 
            
54
way.",
54
way.",
            
n
55
  "num_resources": 0,
n
55
  "num_resources": 1,
            
56
  "num_tags": 3,
56
  "num_tags": 3,
            
57
  "organization": {
57
  "organization": {
            
58
    "approval_status": "approved",
58
    "approval_status": "approved",
            
59
    "created": "2024-11-25T12:11:38.292601",
59
    "created": "2024-11-25T12:11:38.292601",
            
60
    "description": "",
60
    "description": "",
            
61
    "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
61
    "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            
62
    "image_url": "",
62
    "image_url": "",
            
63
    "is_organization": true,
63
    "is_organization": true,
            
64
    "name": "no-organization",
64
    "name": "no-organization",
            
65
    "state": "active",
65
    "state": "active",
            
66
    "title": "No Organization",
66
    "title": "No Organization",
            
67
    "type": "organization"
67
    "type": "organization"
            
68
  },
68
  },
            
69
  "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
69
  "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            
70
  "private": false,
70
  "private": false,
            
71
  "relationships_as_object": [],
71
  "relationships_as_object": [],
            
72
  "relationships_as_subject": [],
72
  "relationships_as_subject": [],
            
t
73
  "resources": [],
t
73
  "resources": [
            
74
    {
            
75
      "cache_last_updated": null,
            
76
      "cache_url": null,
            
77
      "created": "2024-12-16T23:37:09",
            
78
      "data": [
            
79
        "dcterms:title",
            
80
        "dcterms:accessRights",
            
81
        "dcterms:creator",
            
82
        "dcterms:description",
            
83
        "dcterms:issued",
            
84
        "dcterms:language",
            
85
        "dcterms:identifier",
            
86
        "dcat:theme",
            
87
        "dcterms:type",
            
88
        "dcat:keyword",
            
89
        "dcat:landingPage",
            
90
        "dcterms:hasVersion",
            
91
        "dcterms:format",
            
92
        "mls:task",
            
93
        "datacite:isDescribedBy"
            
94
      ],
            
95
      "description": "The json representation of the dataset with its 
            
96
distributions based on DCAT.",
            
97
      "format": "JSON",
            
98
      "hash": "",
            
99
      "id": "24c4b954-6da8-473c-b67a-c677c865d470",
            
100
      "last_modified": "2024-12-16T23:09:29.263638",
            
101
      "metadata_modified": "2024-12-16T23:09:29.273936",
            
102
      "mimetype": "application/json",
            
103
      "mimetype_inner": null,
            
104
      "name": "Original Metadata",
            
105
      "package_id": "fc3f9733-b49e-4d77-b0ca-8e2c1e064b75",
            
106
      "position": 0,
            
107
      "resource_type": null,
            
108
      "size": 1182,
            
109
      "state": "active",
            
110
      "url": 
            
111
resource/24c4b954-6da8-473c-b67a-c677c865d470/download/metadata.json",
            
112
      "url_type": "upload"
            
113
    }
            
114
  ],
            
74
  "services_used_list": "",
115
  "services_used_list": "",
            
75
  "state": "active",
116
  "state": "active",
            
76
  "tags": [
117
  "tags": [
            
77
    {
118
    {
            
78
      "display_name": "Deep Q learning",
119
      "display_name": "Deep Q learning",
            
79
      "id": "2ecb0145-2555-44c0-bee5-f66029b44b20",
120
      "id": "2ecb0145-2555-44c0-bee5-f66029b44b20",
            
80
      "name": "Deep Q learning",
121
      "name": "Deep Q learning",
            
81
      "state": "active",
122
      "state": "active",
            
82
      "vocabulary_id": null
123
      "vocabulary_id": null
            
83
    },
124
    },
            
84
    {
125
    {
            
85
      "display_name": "Hierarchical control",
126
      "display_name": "Hierarchical control",
            
86
      "id": "ad32c88e-8da9-4651-a92b-16609df77e4e",
127
      "id": "ad32c88e-8da9-4651-a92b-16609df77e4e",
            
87
      "name": "Hierarchical control",
128
      "name": "Hierarchical control",
            
88
      "state": "active",
129
      "state": "active",
            
89
      "vocabulary_id": null
130
      "vocabulary_id": null
            
90
    },
131
    },
            
91
    {
132
    {
            
92
      "display_name": "Multi-stage control tasks",
133
      "display_name": "Multi-stage control tasks",
            
93
      "id": "f1762b4b-b92e-477f-9859-9ab28e576d86",
134
      "id": "f1762b4b-b92e-477f-9859-9ab28e576d86",
            
94
      "name": "Multi-stage control tasks",
135
      "name": "Multi-stage control tasks",
            
95
      "state": "active",
136
      "state": "active",
            
96
      "vocabulary_id": null
137
      "vocabulary_id": null
            
97
    }
138
    }
            
98
  ],
139
  ],
            
99
  "title": "A Deep Reinforcement Learning Architecture for Multi-stage 
140
  "title": "A Deep Reinforcement Learning Architecture for Multi-stage 
            
100
Optimal Control",
141
Optimal Control",
            
101
  "type": "dataset",
142
  "type": "dataset",
            
102
  "version": ""
143
  "version": ""
            
103
}
144
}