On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “MOBA”

MOBA-Slice: A Time Slice Based Evaluation Framework of Relative Advantage between Teams in MOBA Gamescs.LG

MOBA-Slice evaluates team advantage in MOBA games using neural networks.

problem Difficulty in evaluating and predicting MOBA game outcomes.

method Time slice based evaluation framework using neural networks.

result MOBA-Slice outperforms existing methods in predicting game results and remaining time.

MOBA games team advantage neural networks evaluation framework AI development

2018-07-22abs ↗pdf ↗

A Confidence-Calibrated MOBA Game Winner Predictorcs.LG

Paper proposes a method to predict MOBA game winners with calibrated confidence.

problem Predicting MOBA game winners with noisy data and uncertain noise.

method A novel confidence-calibration method considering data uncertainty.

result Achieves outstanding expected calibration error (ECE) of 0.57%.

MOBA game confidence calibration League of Legends data uncertainty expected calibration error

2020-06-28abs ↗pdf ↗

MOBA: A multi-objective bounded-abstention model for two-class cost-sensitive problemscs.LG

MOBA model optimizes error rates for two-class cost-sensitive problems.

problem Cost-sensitive classification with ambiguous labels and varying costs.

method Multi-objective bounded-abstention model using genetic algorithm.

result MOBA achieves lower expected costs with known costs and better trade-offs without.

abstention cost-sensitive multi-objective genetic algorithm two-class

2019-05-17abs ↗pdf ↗

Skill-Based Differences in Spatio-Temporal Team Behavior in Defence of The Ancients 2stat.ML

The paper analyzes spatio-temporal behavior in DotA 2, finding skill differences in team dynamics.

problem Understanding skill differences in MOBA team dynamics.

method Data-driven measures of spatio-temporal behavior, including zone changes and time series clustering.

result Professional teams show smaller within-team distances and more zone changes than amateur teams.

MOBA DotA 2 spatio-temporal behavior team dynamics skill level

2016-03-24abs ↗pdf ↗

Neural MMO v1.3: A Massively Multiagent Game Environment for Training and Evaluating Neural Networkscs.LG

Neural MMO simulates MMOs to study multiagent intelligence.

problem Limited research environments for multiagent intelligence.

method Developed a new game environment inspired by MMOs.

result Standard methods can learn interesting behaviors in MMOs.

multiagent systems reinforcement learning game environments emergent behaviors policy gradient

2020-01-31abs ↗pdf ↗