论文信息 - Applications of Machine Learning in Dota 2: Literature Review and Practical Knowledge Sharing

Applications of Machine Learning in Dota 2: Literature Review and Practical Knowledge Sharing

We present the review of recent applications of Machine Learning in Dota 2. It includes prediction of the winning team from the drafting stage of the game, calculating optimal jungling paths, predict the result of teamfights, recommendataion engine for the draft, and detection of in-game roles with emphasis on win prediction from team composition data. Besides that we discuss our own experience with making Dota 2 Machine Learning hachathon and Kaggle competitions.

Peter Romov | Aleksandr Semenov | Daniil Yashkov | Kirill Neklyudov | Daniil Kireev

[1] Diego Klabjan,et al. Skill-based differences in spatio-temporal team behaviour in defence of the Ancients 2 (DotA 2) , 2014, 2014 IEEE Games Media Entertainment.

[2] Atish Agarwala. Learning Dota 2 Team Compositions , 2014 .

[3] Nicholas Kinkade,et al. DOTA 2 Win Prediction , 2015 .

[4] Jean-Philippe Métivier,et al. Mining Tracks of Competitive Video Games , 2014 .

[5] Anders Drachen,et al. Esports Analytics Through Encounter Detection , 2016 .

[6] Hitoshi Mitomo,et al. Leadership development through online gaming , 2012 .

[7] Kaushik Kalyanaraman,et al. To win or not to win ? A prediction model to determine the outcome of a DotA 2 match , 2015 .

[8] D. Perry,et al. How Does He Saw Me ? A Recommendation Engine for Picking Heroes in Dota 2 , 2013 .

[9] Brent E. Harrison,et al. Identifying patterns in combat that are predictive of success in MOBA games , 2014, FDG.

[10] Tianyi Zhang,et al. Predicting the winning side of DotA 2 , 2015 .

[11] W. Marsden. I and J , 2012 .

[12] Marc Herrlich,et al. Classification of Player Roles in the Team-Based Multi-player Game Dota 2 , 2015, ICEC.

[13] Nataliia Pobiedina. On Successful Team Formation , 2013 .

[14] Filip Johansson,et al. Result Prediction by Mining Replays in Dota 2 , 2015 .