kimbring2 / MOBA_RL

Deep Reinforcement Learning for Multiplayer Online Battle Arena
MIT License
74 stars 9 forks source link

Inquiries about the Replay Parser #8

Open Orion-Zheng opened 5 months ago

Orion-Zheng commented 5 months ago

Thank you for sharing of your work! I am very interested in the dota2-replay-parser section of this repo. But I met some problem when running the replay-parser code at this time, probably because some recent changes in the .dem files. I am trying to debug it by my own and hope to get some help.

  1. I am wondering how to get the latest data.json in the dota2_replay folder? It seems some items in it is not up-to-date. https://github.com/kimbring2/MOBA_RL/blob/658652ff8642004a992dcbb29649a45caf349d18/dota2_replay/data.json
  2. I saw you extract some Player Orders' Info from DOTA_UM_SpectatorPlayerUnitOrders packet as supervised data. I am curious about how did you know Players Orders is in this packet and the correct to parse it? Is there any development documentation on these information? Any help will be very appreciated!