MultiAgentLearning/playground

Help wanted

Aperta

#202 aperta il 5 mar 2019

 (6 commenti) (0 reazioni) (0 assegnatari)Python (215 fork)batch import
enhancementhelp wanted

Metriche repository

Star
 (728 stelle)
Metriche merge PR
 (Nessuna PR mergiata in 30 g)

Descrizione

Here are three implementations that the community would really appreciate:

  1. Add in the flames and the direction of movement to the observation: This is here because the top competitors all recreated it.

  2. Make a history function that returns all the states that this agent experienced and an ability to start from any of these states: This is here because it helps a lot with debugging agents and understanding where they are going wrong.

  3. Make a doc that details how agents move: This is here because a lot of folks ask about it and it's an imperative to understand before building an agent in earnest.

Guida contributor