MétaCan
Menu
Back to cohort
Record W3216740773 · doi:10.1109/mlise54096.2021.00112

Uprising E-sports Industry: machine learning/AI improve in-game performance using deep reinforcement learning

2021· article· en· W3216740773 on OpenAlex

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.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEconomics, Econometrics and Finance
TopicSports Analytics and Performance
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsReinforcement learningComputer scienceArtificial intelligenceTraining (meteorology)Deep learningMachine learning

Abstract

fetched live from OpenAlex

With the quick development of machine learning, deep reinforcement learning will have a big influence on E-sports. It can be considered machine learning will help us train E-sports players easily and effectively and give coaches and players some new ideas to train and win the games. Flappy Bird is a game where the players try to keep the bird alive as long as possible and get a high score. Flappy Bird is a good example to prove that the thought is feasible. In this project, a flappy bird training AI is developed based on Q-learning and DQN. The game is played by the models obtained from deep reinforcement learning, and the game is also played by humans. Then get experimental data from these two ways and compare them. For the two ways of playing the game (by AI or manually), there are many similarities in the increased rate of scores as training sessions increase, which means AI can “teach” players how to train to get a higher score. It can be applied to skills and experience-based games and help us to train top players. Maybe it can also be applied to other fields, such as helping engineers escape from potential errors and accidents.

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 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)0.001
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: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.582
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0040.000

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.

Opus teacher head0.025
GPT teacher head0.228
Teacher spread0.203 · 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

Quick stats

Citations10
Published2021
Admission routes1
Has abstractyes

Explore more

Same topicSports Analytics and PerformanceFrench-language works237,207