StarCraft II Learning environment full overview (VIII)

gema.parreno.piqueras
2 min readOct 6, 2018

Lab : Customize the agent

“Hierach?” Talandar Protoss selected order unit quote

Try your own mini-game

You can try your own mini-game by changing the following steps in your pySC2 folder

  • Create your mini-game. You can visit this tutorial that changes DefeatRoaches into DefeatWhatever melee
  • Add your mini-game to the array in pysc2\maps\mini_games.py
  • Add the mini-game name into the Flag config and training_game section of the agent_CNN+LSTM.py
  • Run the agent in your console

If you want to test it against alredy built-in mini-games from DeepMind and Blizzard :

  • Add the mini-game name into the Flag config of the agent_CNN+LSTM.py
  • Run the agent in your console

Your own policy or your own RL agent

You can customize the agent provided in several ways : You can change the policy and still use a DQN agent, that means that you will take another approach to the learning strategy but still use a Neural Network for function approximation. The trade-off between exploration and explotation is challenging and an on-going research topic. A recommended approach by keras-rl authors is Boltzmann-style exploration [3] , so if you feel like, give it a try and feel free to share your results !

Try pre-trained A3C in your own mini-game

Some members of the community — have code A2C and A3C and have generously released a pre-trained agent. You can test your own mini-game, but this is what happens when HallucinIce mini-game was tested

As you can check, the agent learnt to hide and do nothing. Which take to think that not all algos are suitable for all the goals. Watch the results on A3C on HallucinIce mini-game, in which the agent learns to hide and go nothing

--

--