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.

168,932 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “Esports”

Time to Die: Death Prediction in Dota 2 using Deep Learningcs.LG

Deep learning predicts Dota 2 deaths with high precision and recall.

problem Predicting key events like hero deaths in fast-paced esports matches.

method Shared weights deep learning network trained on Dota 2 data.

result 0.377 precision and 0.725 recall in predicting deaths within 5 seconds.

Dota 2 Deep Learning Predictive Analytics Esports Telemetry Data

2019-05-21abs ↗pdf ↗

SC2EGSet: StarCraft II Esport Replay and Game-state Datasetcs.LG

Extracts StarCraft II tournament data for AI and ML studies.

problem Lack of accessible esports data for scientific use.

method Gathered and processed StarCraft II tournament replays using an API parser library.

result The largest publicly available StarCraft II esports dataset.

StarCraft II esports replay dataset AI ML

2022-07-07abs ↗pdf ↗

Valuing Player Actions in Counter-Strike: Global Offensivecs.AI

Researchers create a framework to value player actions in CSGO.

problem Lack of accessible data and analytical frameworks for esports players.

method Data model, graph distance measure, context-aware framework.

result Demonstrated framework's consistency and independence compared to existing methods.

esports counter-strike global offensive player valuation graph distance

2020-11-02abs ↗pdf ↗

Dota 2 with Large Scale Deep Reinforcement Learningcs.LG

OpenAI Five defeated Dota 2 champions using deep reinforcement learning.

problem Complex, continuous state-action spaces in Dota 2.

method Deep reinforcement learning, distributed training, self-play.

result Superhuman performance in Dota 2 achieved through reinforcement learning.

Dota 2 Deep Reinforcement Learning OpenAI Superhuman Performance Continuous State-Action Spaces

2019-12-13abs ↗pdf ↗

Voting Participation and Engagement in Blockchain-Based Fan Tokensq-fin.GN

Blockchain fan tokens boost sports fan engagement by 50%.

problem Low fan engagement in sports decisions.

method Analyzed 3,576 fan token polls to identify determinants of participation.

result Fan tokens engage 4,003 participants per poll, 50% of token holders.

Blockchain Fan Tokens Sports Engagement Voting Participation Crypto Assets

2024-04-13abs ↗pdf ↗