{
    "experiment": "A",
    "trainenv": {
        "stop_on_collision": false,
        "use_idm": true
    },
    "policy": {
        "learning_rate": 0.0003,
        "learning_rate_decay": 1.0,
        "hidden_layer_size": 40,
        "n_hidden_layers": 2,
        "activation": 0
    },
    "train_epochs": 300,
    "seed": 0
}