Financial control of the evolution of autonomous non-player characters
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This study prototypes a method of evolving autonomous agents that can act as non-player characters (NPCs) in a game. The agents move based on information about their local environment and have evolved weapons, armor, ability to take damage, and movement factors. The creation of the agent is divided into two phases. In the first, a population of competent movement controllers are evolved. In the second, agents start with a competent movement controller and evolve weapons, levels of armor, number of hitpoints, and numbers of movement factors. The movement controller continues to evolve in the second phase. The evolution of the agent's equipment is constrained by a budget together with a price for each type of object the agent can have. The gene specifying the agent's equipment is in the form of a "wish list" of equipment, traversed left-to-right, with the agent buying items from the list as long as its budget suffices. A agent that is a more dangerous opponent can be evolved by giving it a larger budget. A group of experiment are performed that demonstrate that the budget can be used to control an agent's toughness. Additional experiments show that changing the price list for different items can also be used to control the types of agents that evolve. Pitfalls in the selection of the fitness function for the agents are discussed.
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.
Full frame distilled prediction
Teacher imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it