Bibliographic record
Abstract
Recent Computer Role Playing Games such as Bethesda’s The Elder Scrolls V: Skyrim and Nintendo’s The Legend of Zelda: Breath of the Wild, have entranced us with their expansive, complex worlds. However, the Non-Player Characters (NPCs) in these games remain stale and lackluster outside of scripted events. This is, in part, because game engines generally do not simulate emotions in their NPCs while they wander in the world. Wouldn't these games be much more interesting, potentially even more re-playable, if NPCs reacted more appropriately to the situations they find themselves in?To be able to do this, designers need an engine that models emotion, based on inputs available in the game world and from other designer-defined character elements such as personality, goals, and mood. A full-fledged cognitive architecture could fulfill this task, but it would likely be much too inefficient for use in a real-time environment like a game.There are many psychological models of emotion but only a few have been explored for video game applications. A game requires an emotion engine which generates believable results to enhance NPC agency and player engagement. Unlike AI agents and simulations of cognitive psychology theories, an emotion engine for games does not need to be correct or even justifiable. This enables the exploration of a variety of emotion theories that have not been actively considered for games. One such theory is Plutchik's psychoevolutionary synthesis. He proposes a method of organizing emotions into a cone, where the intensity of an emotion increases as one moves up the sides. It also postulates that primary emotions in the model can be arranged in opposing pairs and that other emotions can be composed from the primary emotions and their intensities. This allows for greater flexibility in the number and type of emotions to include, whereas most models that have been used before define a closed set of emotion types—a serious constraint on designer's freedom. A second theory, Lazarus's cognitive appraisal, better describes emotion elicitation and behaviour selection, and appears to integrate well with Plutchik's work.An emotion engine based on simplified versions of psychoevolutionary synthesis and cognitive appraisal is an understudied approach towards emotional NPCs. Together with readily identifiable elements of emotion processing, such as attention and action selection, an engine can be designed and customized to meet the needs of game designers with minimal impact on computational resources.We will present an overview of some existing cognitive architectures and emotion engines followed by a description of key elements in psychoevolutionary synthesis and cognitive appraisal. Next we list some requirements for an emotion engine for NPCs and how our selected emotion theories meet them. Finally, we propose a design and a collection of game-oriented test scenarios to illustrate how our design handles various facets of NPC emotional responses.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.002 | 0.008 |
| Scholarly communication | 0.006 | 0.004 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.012 | 0.002 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".