Oleksii Kachaiev

To answer this question I need to have a GPU 😀 And based on the schedule of other experiments I will be able to run it tomorrow or the day...

Oh, BTW. Found another detail I have to flesh out first: right now evaluation only works against other agents, PvE games are not supported. It's quite easy to cover, so...

Sorry :) It stands for "player vs. environment" (like, built-in bot). In comparison to PvP, as "player vs. player"

I have a working version of microrts integrated with PettingZoo to expose each unit in the game as independent agent :) I assume you are describing less "extreme" API where...

Absolutely! I'll dig it up tomorrow

Okay, I completely blinked on this. This is (partially) the code I'm using in my experiments. I tried to cherry-pick it without any dependencies on my implementation of the environment....

``` from pettingzoo import AECEnv from pettingzoo.utils import agent_selector class MicroRTSAEC(AECEnv, MicroRTSGridModeSharedMemVecEnv): def __init__( self, opponent, agent_vision_patch=(5,5), partial_obs=False, max_steps=2000, render_theme=2, frame_skip=0, map_path="maps/10x10/basesTwoWorkers10x10.xml", reward_weight=np.array([0.0, 1.0, 0.0, 0.0, 0.0, 5.0]), ): self.agent_vision_patch...

@BolunDai0216 Absolutely! @vwxyzjn if my memory doesn't fail me, chess is also implemented as AEC. So the API would look the same. I meant the implementation would be easier with...

Yeah, I think extending `TripletMarginLoss` is a good choice (also, semantically it makes a lot of sense). I will submit a PR as soon as first draft is ready!

@ibebrett Not as of now, feel free to chime in!