MétaCan
Menu
Back to cohort
Record W2767141304 · doi:10.1109/cig.2017.8080452

Improving hearthstone AI by learning high-level rollout policies and bucketing chance node events

2017· article· en· W2767141304 on OpenAlexaff
Shuyi Zhang, Michael Buro

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicArtificial Intelligence in Games
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsComputer scienceMonte Carlo tree searchEntertainmentAdversaryVideo gameState (computer science)Node (physics)Artificial intelligenceGame treeAction (physics)Computer securitySequential gameMultimediaGame theoryProgramming languageMonte Carlo methodMathematical economicsEngineeringVisual arts

Abstract

fetched live from OpenAlex

Modern board, card, and video games are challenging domains for AI research due to their complex game mechanics and large state and action spaces. For instance, in Hearthstone - a popular collectible card (CC) (video) game developed by Blizzard Entertainment - two players first construct their own card decks from over 1,000 different cards and then draw and play cards to cast spells, select weapons, and combat minions and the opponent's hero. Players' turns are often comprised of multiple actions, including drawing new cards, which leads to enormous branching factors that pose a problem for state-of-the-art heuristic search methods. In this paper we first present two ideas to tackle this problem, namely by reducing chance node branching factors by bucketing events with similar outcomes, and using high-level policy networks for guiding Monte Carlo Tree Search rollouts. We then apply these ideas to the game of Hearthstone and show significant improvements over a state-of-the-art AI system for this game.

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.008
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.006
Threshold uncertainty score0.017

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.008
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0010.001
Scholarly communication0.0010.003
Open science0.0020.002
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0050.001

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 head0.034
GPT teacher head0.306
Teacher spread0.272 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
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

Citations25
Published2017
Admission routes1
Has abstractyes

Explore more

Same topicArtificial Intelligence in GamesFrench-language works237,207