Changes

              
    

          
          
        
        

            
f
1
{
f
1
{
            
2
  "access_rights": "",
2
  "access_rights": "",
            
3
  "author": "Laixi Shi",
3
  "author": "Laixi Shi",
            
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.2404.18909",
7
  "defined_in": "https://doi.org/10.48550/arXiv.2404.18909",
            
8
  "doi": "10.57702/f3z2d670",
8
  "doi": "10.57702/f3z2d670",
            
n
9
  "doi_date_published": null,
n
9
  "doi_date_published": "2024-12-02",
            
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": "Eric Mazumdar",
15
      "extra_author": "Eric Mazumdar",
            
16
      "orcid": ""
16
      "orcid": ""
            
17
    },
17
    },
            
18
    {
18
    {
            
19
      "extra_author": "Yuejie Chi",
19
      "extra_author": "Yuejie Chi",
            
20
      "orcid": ""
20
      "orcid": ""
            
21
    },
21
    },
            
22
    {
22
    {
            
23
      "extra_author": "Adam Wierman",
23
      "extra_author": "Adam Wierman",
            
24
      "orcid": ""
24
      "orcid": ""
            
25
    }
25
    }
            
26
  ],
26
  ],
            
27
  "groups": [
27
  "groups": [
            
28
    {
28
    {
            
29
      "description": "",
29
      "description": "",
            
30
      "display_name": "Game Theory",
30
      "display_name": "Game Theory",
            
31
      "id": "8ca5b88f-e5f4-48eb-b5d7-4718711e5fa6",
31
      "id": "8ca5b88f-e5f4-48eb-b5d7-4718711e5fa6",
            
32
      "image_display_url": "",
32
      "image_display_url": "",
            
33
      "name": "game-theory",
33
      "name": "game-theory",
            
34
      "title": "Game Theory"
34
      "title": "Game Theory"
            
35
    },
35
    },
            
36
    {
36
    {
            
37
      "description": "",
37
      "description": "",
            
38
      "display_name": "Multi-Agent Systems",
38
      "display_name": "Multi-Agent Systems",
            
39
      "id": "f6b3fbc4-745c-449d-a7c0-dc1d143b3d58",
39
      "id": "f6b3fbc4-745c-449d-a7c0-dc1d143b3d58",
            
40
      "image_display_url": "",
40
      "image_display_url": "",
            
41
      "name": "multi-agent-systems",
41
      "name": "multi-agent-systems",
            
42
      "title": "Multi-Agent Systems"
42
      "title": "Multi-Agent Systems"
            
43
    },
43
    },
            
44
    {
44
    {
            
45
      "description": "",
45
      "description": "",
            
46
      "display_name": "Reinforcement Learning",
46
      "display_name": "Reinforcement Learning",
            
47
      "id": "5f9e20df-0af0-4b7e-9637-e244d4a99379",
47
      "id": "5f9e20df-0af0-4b7e-9637-e244d4a99379",
            
48
      "image_display_url": "",
48
      "image_display_url": "",
            
49
      "name": "reinforcement-learning",
49
      "name": "reinforcement-learning",
            
50
      "title": "Reinforcement Learning"
50
      "title": "Reinforcement Learning"
            
51
    }
51
    }
            
52
  ],
52
  ],
            
53
  "id": "00a88f9a-08f6-4a4d-b938-b40be14bc503",
53
  "id": "00a88f9a-08f6-4a4d-b938-b40be14bc503",
            
54
  "isopen": false,
54
  "isopen": false,
            
55
  "landing_page": "https://arxiv.org/abs/2106.09453",
55
  "landing_page": "https://arxiv.org/abs/2106.09453",
            
56
  "license_title": null,
56
  "license_title": null,
            
57
  "link_orkg": "",
57
  "link_orkg": "",
            
58
  "metadata_created": "2024-12-02T23:21:07.607149",
58
  "metadata_created": "2024-12-02T23:21:07.607149",
            
n
59
  "metadata_modified": "2024-12-02T23:21:07.607156",
n
59
  "metadata_modified": "2024-12-02T23:21:08.157513",
            
60
  "name": 
60
  "name": 
            
61
gent-reinforcement-learning-in-the-face-of-environmental-uncertainty",
61
gent-reinforcement-learning-in-the-face-of-environmental-uncertainty",
            
62
  "notes": "To overcome the sim-to-real gap in reinforcement learning 
62
  "notes": "To overcome the sim-to-real gap in reinforcement learning 
            
63
(RL), learned policies must maintain robustness against environmental 
63
(RL), learned policies must maintain robustness against environmental 
            
64
uncertainties. While robust RL has been widely studied in single-agent 
64
uncertainties. While robust RL has been widely studied in single-agent 
            
65
regimes, in multi-agent environments, the problem remains 
65
regimes, in multi-agent environments, the problem remains 
            
66
understudied\u2014despite the fact that the problems posed by 
66
understudied\u2014despite the fact that the problems posed by 
            
67
environmental uncertainties are often exacerbated by strategic 
67
environmental uncertainties are often exacerbated by strategic 
            
68
interactions. This work focuses on learning in distributionally robust 
68
interactions. This work focuses on learning in distributionally robust 
            
69
Markov games (RMGs), a robust variant of standard Markov games, 
69
Markov games (RMGs), a robust variant of standard Markov games, 
            
70
wherein each agent aims to learn a policy that maximizes its own 
70
wherein each agent aims to learn a policy that maximizes its own 
            
71
worst-case performance when the deployed environment deviates within 
71
worst-case performance when the deployed environment deviates within 
            
72
its own prescribed uncertainty set. This results in a set of robust 
72
its own prescribed uncertainty set. This results in a set of robust 
            
73
equilibrium strategies for all agents that align with classic notions 
73
equilibrium strategies for all agents that align with classic notions 
            
74
of game-theoretic equilibria.",
74
of game-theoretic equilibria.",
            
n
75
  "num_resources": 0,
n
75
  "num_resources": 1,
            
76
  "num_tags": 3,
76
  "num_tags": 3,
            
77
  "organization": {
77
  "organization": {
            
78
    "approval_status": "approved",
78
    "approval_status": "approved",
            
79
    "created": "2024-11-25T12:11:38.292601",
79
    "created": "2024-11-25T12:11:38.292601",
            
80
    "description": "",
80
    "description": "",
            
81
    "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
81
    "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            
82
    "image_url": "",
82
    "image_url": "",
            
83
    "is_organization": true,
83
    "is_organization": true,
            
84
    "name": "no-organization",
84
    "name": "no-organization",
            
85
    "state": "active",
85
    "state": "active",
            
86
    "title": "No Organization",
86
    "title": "No Organization",
            
87
    "type": "organization"
87
    "type": "organization"
            
88
  },
88
  },
            
89
  "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
89
  "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            
90
  "private": false,
90
  "private": false,
            
91
  "relationships_as_object": [],
91
  "relationships_as_object": [],
            
92
  "relationships_as_subject": [],
92
  "relationships_as_subject": [],
            
t
93
  "resources": [],
t
93
  "resources": [
            
94
    {
            
95
      "cache_last_updated": null,
            
96
      "cache_url": null,
            
97
      "created": "2024-12-03T00:20:35",
            
98
      "data": [
            
99
        "dcterms:title",
            
100
        "dcterms:accessRights",
            
101
        "dcterms:creator",
            
102
        "dcterms:description",
            
103
        "dcterms:issued",
            
104
        "dcterms:language",
            
105
        "dcterms:identifier",
            
106
        "dcat:theme",
            
107
        "dcterms:type",
            
108
        "dcat:keyword",
            
109
        "dcat:landingPage",
            
110
        "dcterms:hasVersion",
            
111
        "dcterms:format",
            
112
        "mls:task",
            
113
        "datacite:isDescribedBy"
            
114
      ],
            
115
      "description": "The json representation of the dataset with its 
            
116
distributions based on DCAT.",
            
117
      "format": "JSON",
            
118
      "hash": "",
            
119
      "id": "15461b39-5b32-4e24-9649-6c1b0b087df1",
            
120
      "last_modified": "2024-12-02T23:21:08.149895",
            
121
      "metadata_modified": "2024-12-02T23:21:08.160442",
            
122
      "mimetype": "application/json",
            
123
      "mimetype_inner": null,
            
124
      "name": "Original Metadata",
            
125
      "package_id": "00a88f9a-08f6-4a4d-b938-b40be14bc503",
            
126
      "position": 0,
            
127
      "resource_type": null,
            
128
      "size": 1609,
            
129
      "state": "active",
            
130
      "url": 
            
131
resource/15461b39-5b32-4e24-9649-6c1b0b087df1/download/metadata.json",
            
132
      "url_type": "upload"
            
133
    }
            
134
  ],
            
94
  "services_used_list": "",
135
  "services_used_list": "",
            
95
  "state": "active",
136
  "state": "active",
            
96
  "tags": [
137
  "tags": [
            
97
    {
138
    {
            
98
      "display_name": "game-theoretic equilibria",
139
      "display_name": "game-theoretic equilibria",
            
99
      "id": "d79a8a76-ceda-4b71-9c3e-0db0370204dc",
140
      "id": "d79a8a76-ceda-4b71-9c3e-0db0370204dc",
            
100
      "name": "game-theoretic equilibria",
141
      "name": "game-theoretic equilibria",
            
101
      "state": "active",
142
      "state": "active",
            
102
      "vocabulary_id": null
143
      "vocabulary_id": null
            
103
    },
144
    },
            
104
    {
145
    {
            
105
      "display_name": "multi-agent RL",
146
      "display_name": "multi-agent RL",
            
106
      "id": "e5ed8772-2330-43f6-81a2-e41ce6d2b2a3",
147
      "id": "e5ed8772-2330-43f6-81a2-e41ce6d2b2a3",
            
107
      "name": "multi-agent RL",
148
      "name": "multi-agent RL",
            
108
      "state": "active",
149
      "state": "active",
            
109
      "vocabulary_id": null
150
      "vocabulary_id": null
            
110
    },
151
    },
            
111
    {
152
    {
            
112
      "display_name": "robust RL",
153
      "display_name": "robust RL",
            
113
      "id": "0aefa7c2-8c20-4b50-b721-3bb9a241008f",
154
      "id": "0aefa7c2-8c20-4b50-b721-3bb9a241008f",
            
114
      "name": "robust RL",
155
      "name": "robust RL",
            
115
      "state": "active",
156
      "state": "active",
            
116
      "vocabulary_id": null
157
      "vocabulary_id": null
            
117
    }
158
    }
            
118
  ],
159
  ],
            
119
  "title": "Sample-Efficient Robust Multi-Agent Reinforcement Learning 
160
  "title": "Sample-Efficient Robust Multi-Agent Reinforcement Learning 
            
120
in the Face of Environmental Uncertainty",
161
in the Face of Environmental Uncertainty",
            
121
  "type": "dataset",
162
  "type": "dataset",
            
122
  "version": ""
163
  "version": ""
            
123
}
164
}