What does the actions listed in sample configs means? about reagent HOT 3 CLOSED

@MisterTea Any info or suggestion will be very helpful. I tried to print details during evaluation and I still haven't figure it out

Float State Features = [{'0': 0.16316721, '1': 1.7206059, '2': -0.22225317, '3': -2.8040316}]
Prediction: [{'4': -1.6168417, '5': 0.6317559}]
Max Q values = 5
Action Index = 1

My guess so far is that actions values from dqn_example.json is mapped as
{'4': 0, '5': 1}

Thanks

from reagent.

Hey! The actions are integers starting where the state integers leave off. In this case, the state features are [0...3]

The action feature IDs and state feature IDs can't overlap, which is why the actions are not 0 and 1

from reagent.

Thank you so much @MisterTea.

from reagent.