See world model on Wiktionary
{
"etymology_links": [
[
"world",
"world#English"
],
[
"model",
"model#English"
]
],
"etymology_templates": [
{
"args": {
"1": "Compound"
},
"expansion": "Compound",
"name": "glossary"
},
{
"args": {
"1": "en",
"2": "world",
"3": "model"
},
"expansion": "Compound of world + model",
"name": "com+"
}
],
"etymology_text": "Compound of world + model.",
"forms": [
{
"form": "world models",
"tags": [
"plural"
]
}
],
"head_templates": [
{
"args": {
"1": "s"
},
"expansion": "world model (plural world models)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "English entries with incorrect language header",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with 1 entry",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w"
},
{
"kind": "other",
"langcode": "en",
"name": "Artificial intelligence",
"orig": "en:Artificial intelligence",
"parents": [],
"source": "w"
}
],
"examples": [
{
"bold_text_offsets": [
[
85,
96
],
[
85,
97
],
[
112,
123
]
],
"ref": "1983, James F. Allen, Johannes A. Koomen, “Planning using a temporal world model”, in Proceedings of the Eighth International Joint Conference on Artificial Intelligence, page 741:",
"text": "Current problem solving systems are constrained in their applicability by inadequate world models. We suggest a world model based on a temporal logic. This approach allows the problem solver to gather constraints on the ordering of actions without having to commit to an ordering when a conflict is detected.",
"type": "quotation"
},
{
"bold_text_offsets": [
[
97,
109
],
[
213,
225
]
],
"ref": "2018, David Ha, Jürgen Schmidhuber, “World Models”, in arXiv, page 2:",
"text": "In this work, we build probabilistic generative models of OpenAI Gym environments. The RNN-based world models are trained using collected observations recorded from the actual game environment. After training the world models, we can use them mimic the complete environment and train agents using them.",
"type": "quotation"
},
{
"bold_text_offsets": [
[
188,
199
]
],
"ref": "2024 February 17, @ylecun, Twitter:",
"text": "The generation of mostly realistic-looking videos from prompts *does not* indicate that a system understands the physical world. Generation is very different from causal prediction from a world model.",
"type": "quotation"
},
{
"bold_text_offsets": [
[
112,
123
],
[
125,
137
]
],
"ref": "2026 January 3, Melissa Heikkilä, “Lunch with the FT: Yann LeCun”, in FT Weekend (Life & Arts section), London: The Financial Times Ltd., →ISSN, →OCLC, page 3:",
"text": "His solution for achieving that [human-level intelligence] relies on an architecture called V-JEPA, a so-called world model. World models aim to understand the physical world by learning from videos and spatial data, rather than just language.",
"type": "quotation"
}
],
"glosses": [
"A predictive model that has been internalised by an agent which is used to forecast what consequences its actions will have on the environment (i.e. world) that it interacts with."
],
"id": "en-world_model-en-noun-vHofMCnK",
"links": [
[
"artificial intelligence",
"artificial intelligence"
],
[
"predictive",
"predictive"
],
[
"model",
"model"
],
[
"internalise",
"internalise"
],
[
"agent",
"agent"
],
[
"consequence",
"consequence"
],
[
"action",
"action"
],
[
"environment",
"environment"
],
[
"interact",
"interact"
]
],
"qualifier": "artificial intelligence; reinforcement learning; artificial intelligence; reinforcement learning",
"raw_glosses": [
"(artificial intelligence, reinforcement learning) A predictive model that has been internalised by an agent which is used to forecast what consequences its actions will have on the environment (i.e. world) that it interacts with."
],
"related": [
{
"word": "implicit modeling"
},
{
"word": "mental model"
},
{
"word": "weltanschauung"
},
{
"word": "worldview"
}
]
}
],
"word": "world model"
}
{
"etymology_links": [
[
"world",
"world#English"
],
[
"model",
"model#English"
]
],
"etymology_templates": [
{
"args": {
"1": "Compound"
},
"expansion": "Compound",
"name": "glossary"
},
{
"args": {
"1": "en",
"2": "world",
"3": "model"
},
"expansion": "Compound of world + model",
"name": "com+"
}
],
"etymology_text": "Compound of world + model.",
"forms": [
{
"form": "world models",
"tags": [
"plural"
]
}
],
"head_templates": [
{
"args": {
"1": "s"
},
"expansion": "world model (plural world models)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"related": [
{
"word": "implicit modeling"
},
{
"word": "mental model"
},
{
"word": "weltanschauung"
},
{
"word": "worldview"
}
],
"senses": [
{
"categories": [
"English compound terms",
"English countable nouns",
"English entries with incorrect language header",
"English lemmas",
"English multiword terms",
"English nouns",
"English terms with quotations",
"Pages with 1 entry",
"Pages with entries",
"en:Artificial intelligence"
],
"examples": [
{
"bold_text_offsets": [
[
85,
96
],
[
85,
97
],
[
112,
123
]
],
"ref": "1983, James F. Allen, Johannes A. Koomen, “Planning using a temporal world model”, in Proceedings of the Eighth International Joint Conference on Artificial Intelligence, page 741:",
"text": "Current problem solving systems are constrained in their applicability by inadequate world models. We suggest a world model based on a temporal logic. This approach allows the problem solver to gather constraints on the ordering of actions without having to commit to an ordering when a conflict is detected.",
"type": "quotation"
},
{
"bold_text_offsets": [
[
97,
109
],
[
213,
225
]
],
"ref": "2018, David Ha, Jürgen Schmidhuber, “World Models”, in arXiv, page 2:",
"text": "In this work, we build probabilistic generative models of OpenAI Gym environments. The RNN-based world models are trained using collected observations recorded from the actual game environment. After training the world models, we can use them mimic the complete environment and train agents using them.",
"type": "quotation"
},
{
"bold_text_offsets": [
[
188,
199
]
],
"ref": "2024 February 17, @ylecun, Twitter:",
"text": "The generation of mostly realistic-looking videos from prompts *does not* indicate that a system understands the physical world. Generation is very different from causal prediction from a world model.",
"type": "quotation"
},
{
"bold_text_offsets": [
[
112,
123
],
[
125,
137
]
],
"ref": "2026 January 3, Melissa Heikkilä, “Lunch with the FT: Yann LeCun”, in FT Weekend (Life & Arts section), London: The Financial Times Ltd., →ISSN, →OCLC, page 3:",
"text": "His solution for achieving that [human-level intelligence] relies on an architecture called V-JEPA, a so-called world model. World models aim to understand the physical world by learning from videos and spatial data, rather than just language.",
"type": "quotation"
}
],
"glosses": [
"A predictive model that has been internalised by an agent which is used to forecast what consequences its actions will have on the environment (i.e. world) that it interacts with."
],
"links": [
[
"artificial intelligence",
"artificial intelligence"
],
[
"predictive",
"predictive"
],
[
"model",
"model"
],
[
"internalise",
"internalise"
],
[
"agent",
"agent"
],
[
"consequence",
"consequence"
],
[
"action",
"action"
],
[
"environment",
"environment"
],
[
"interact",
"interact"
]
],
"qualifier": "artificial intelligence; reinforcement learning; artificial intelligence; reinforcement learning",
"raw_glosses": [
"(artificial intelligence, reinforcement learning) A predictive model that has been internalised by an agent which is used to forecast what consequences its actions will have on the environment (i.e. world) that it interacts with."
]
}
],
"word": "world model"
}
Download raw JSONL data for world model meaning in All languages combined (3.6kB)
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2026-10-03 from the enwiktionary dump dated 2026-09-02 using wiktextract (1a05e46 and e3d6d4e). The data shown on this site has been post-processed and various details (e.g., extra categories) removed, some information disambiguated, and additional data merged from other sources. See the raw data download page for the unprocessed wiktextract data.
If you use this data in academic research, please cite Tatu Ylonen: Wiktextract: Wiktionary as Machine-Readable Structured Data, Proceedings of the 13th Conference on Language Resources and Evaluation (LREC), pp. 1317-1325, Marseille, 20-25 June 2022. Linking to the relevant page(s) under https://kaikki.org would also be greatly appreciated.