MétaCan
Menu
Back to cohort
Record W2976261784 · doi:10.1109/cig.2019.8848093

Towards Procedurally Generated Languages for Non-playable Characters in Video Games

2019· article· en· W2976261784 on OpenAlexaff
Joshua Sirota, Vadim Bulitko, Matthew Brown, Sergio Poo Hernandez

Bibliographic record

Venue2019 IEEE Conference on Games (CoG) · 2019
Typearticle
Languageen
FieldComputer Science
TopicArtificial Intelligence in Games
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsComputer scienceNeuroevolutionCommunication sourceArchitectureVideo gameIllusionAtmosphere (unit)Artificial intelligenceArtificial neural networkMultimediaHuman–computer interactionComputer network

Abstract

fetched live from OpenAlex

Non-playable characters (NPCs) enhance a player's immersion in a video game. Communications among NPCs create atmosphere and, in some games, are a core element of the gameplay. Yet, the majority of games manually script inter-NPC communications creating only an illusion of such exchanges. Doing so is laborious and results in fixed interactions which may not respond to the player's actions or changes in the environment. In this paper we propose procedural content generation (PCG) for emergent inter-NPC languages. Indeed, recent research demonstrated that deep neural networks can be trained to develop an artificial language to communicate with each other. The work used a fixed, handcrafted network architecture identical for both the sending and receiving agents. We extend the work by using neuroevolution for both the sender and the receiver. In doing so we evolve both the architecture and weights of the agents and show that they successfully develop novel languages to communicate among themselves.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Insufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.456
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0020.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.032
GPT teacher head0.299
Teacher spread0.267 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designBench or experimental
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations2
Published2019
Admission routes1
Has abstractyes

Explore more

Same venue2019 IEEE Conference on Games (CoG)Same topicArtificial Intelligence in GamesFrench-language works237,207