search

moratodpg / imp_marl

IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL
Apache License 2.0
35 stars 5 forks source link

Main readme PR #47

Closed moratodpg closed 1 year ago

PaLeroy commented 1 year ago

I suggest this: For me, this is self-explanatory. We do not need to import in a README and the lines are really easy to grasp, I feel adding comments is really not nice.

env = Struct({'n_comp': 3,
               'discount_reward': 0.95,
               'k_comp': 2,
               'env_correlation': False,
               'campaign_cost': False})

obs, rewards_sum, done = env.reset(), 0, False
while not done:
    actions = {f"agent_{i}": random.randint(0,2) for i in range(3)}
    obs, rewards, done, insp_outcomes = env.step(actions)
moratodpg commented 1 year ago

I am not sure everybody will be able to run this (without the importing packages). But I will change it.