Extending Heuristic Knowledge Transfer for General Game Playing
Bibliographic record
Abstract
General Game Playing (GGP) is a field of study in which artificial agents are required to compete in games whose rules are not known until runtime. Monte Carlo Tree Search (MCTS) is popular in this domain for its ability to quickly simulate many instances of a game and run in whatever time it is given. Heuristics may be used to guide these simulations, but since the game is not known in advance, a typical MCTS agent cannot know which heuristics are useful, and must expend precious time to discover them. However, an agent able to take advantage of prior knowledge from other games can do better. This paper extends our publication at the 2024 IEEE Conference on Games [1]. As in that paper, we present a technique for automatically transferring heuristic knowledge between distinct, but similar, games. We show that this leads to better performance in games within the GGP framework, especially when initialization time is short, and we show that negative transfer is possible to detect and avoid. Unique to this paper, we give experimental results for an alternate method of negative transfer protection, and explore the application of our methods to single-player games.
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 | 0.003 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.004 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
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.
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".