• ①LoLというオンラインゲームを誰にでもわかりやすいように説明してください。
  • ②LoLというゲームの面白さをアピールしてください。
  • ③LoLというゲームを始める際にどうすればいいか教えてください。
  • ④LoLのゲームで、操作が簡単なチャンピオンをいくつか教えて。
  • 総括




Simple Idea Made Prediction Model Understand the Difference in Time-Dependent Features of Champions 【LoL】【ML】

My last article was somewhat abstract, writing about the concept of "Bli2kun Project".
This time, I'm reporting on a simple idea that yielded some interesting results. I hope you will enjoy reading it more than last time.


  • Challenge: How to Get the Model to Learn the Different Timing of Different Champions' Power Spikes
  • Approach: Simple Idea Solved This Problem!
    • How to determine the length of the game be split?
  • Results: Model Captures the Difference in the Characteristics of Champions
    • Result of the model learning early game (~25min) data
    • Result of the model learning middle game (25min~35min) data
    • Result of the model learning late game (35min~) data
  • Finally...



"Bli2kun Project" Start!! Predict the Win Team from Picked Champions Using ML or DL methods.【LoL】

Hey guys, how are you enjoying Worlds 2020?
I enjoy watching WCS games myself, of course. I just started LoL this spring after Corona, and a lot of the pro games are exciting for me. I try to share my impressions and original content on my blog.

By the way, have you ever heard of the "Bliz-kun" model that appeared on the LJL game broadcast? It's a system for predicting winnings rate after the draft and in the middle of a game. I haven't seen anything like this outside of the LJL and LPL. (I was watching games in the LJL, LCK, LPL, and LEC regions this summer.) I like the system as an element of spectatorship, and I'm technically interested in it because it's close to my field of study.

As you know, no such system for predicting the odds of winning has appeared in the WCS. Then I'm going to try to mimic this system myself, which is the main purpose of this article. I decided to call this challenge the "Bli2kun Project".

In this article, I'm going to write about the ideas I tried and the interesting results I got, not the program code and other details.


  •  Overview of "Bli2kun Project" Version 1
    • Collecting Data
    • Machine Learning Model which I Used
    • Input Shape for the Model: One-hot Encoding
    • Problem Setting
    • Motivation of Version1
    • Future Works
  • Test & Trials
    • Trials Using the Matches in WCS Group Stage
      • Group Stage Day5 Tiebreaker: Suning vs G2:Suning Win
      • Group Stage Day6: JDG vs DRX:JDG Win
      • Group Stage Day8: DRX vs TES:TES Win
  • Appendix: Champion Importance which Bli2-kun learned
  • Finally...






  •  まず最初に:問題設定の確認
  • Bli2君アップデート内容を解説!
    • Embedding
    • MultiHead Attention
    • Additive Attention
  • その他のポイント
    • 時間帯ごとにモデルを学習させるのは変わらず
    • 使用するデータを前回から増やす
  • Case Study:TES vs Suning Game1
    • MultiHead Attentionのattention可視化
    • Additive Attentionのattention可視化
  • 最後に



BanPickからDWGとG2の違いを読み解く... Semifinal DWG vs G2【LoL WCS2020】【観戦日記】【ドラフト考察】

みなさん、先日のDWG vs G2のSemifinalはいかがでしたか。

筆者はG2を応援していたのと、PICK'EMもG2 winを予想していたのでショックが大きいです... 試合内容としてもGame2以外はDWGが圧倒してスノーボールを決めた印象が強く、個人的に面白くないので、今回の観戦日記は、シリーズを通したドラフトについて考える内容にしようと思います。

もう少し真面目な理由を挙げると、LJL韓国語通訳のスイニャンさん(@shuiniao)の、DWGのadc Ghostの試合後インタビューを日本語訳してくれたツイートによると、Ban Pickの段階でDWGがかなり上手くやっていたようです。



  • シリーズを通したBanPickの一覧
  • mid偏重のG2に対してバランスのいいDWGのピック
    • midの懐が深いDWG
    • topの懐も深いDWG
  • 最後に