hyperparams.py

value_epoch = {
    'plunder': 1,
    'chaser': 1, 
    'miner': 9, 
    'climber': 9,
    'bigfish': 9,
    'dodgeball': 9,
    'maze': 9,
    'leaper': 9,
    'fruitbot': 9, 
    'bossfight': 9,
    'jumper': 9,
    'ninja': 9,
    'starpilot': 9, 
    'coinrun': 9,
    'heist': 9,
    'caveflyer': 9,
} 

value_freq = {
    'plunder': 8,
    'chaser': 1,
    'miner': 32,
    'climber': 1,
    'bigfish': 32,
    'dodgeball': 32,
    'maze': 1,
    'leaper': 1,
    'fruitbot': 1, 
    'bossfight': 1,
    'jumper': 1,
    'ninja': 1,
    'starpilot': 1, 
    'coinrun': 1,
    'heist': 1,
    'caveflyer': 1,
}

adv_loss_coef = {
    'plunder': 0.3,
    'chaser': 0.15,
    'miner': 0.25,
    'climber': 0.05,
    'bigfish': 0.05,
    'dodgeball': 0.25,
    'maze': 0.25,
    'leaper': 0.25, 
    'fruitbot': 0.25, 
    'bossfight': 0.25,
    'jumper': 0.25,
    'ninja': 0.25,
    'starpilot': 0.25,
    'coinrun': 0.25,
    'heist': 0.25,
    'caveflyer': 0.25,
}

order_loss_coef = {
    'plunder': 0.1,
    'chaser': 0.001,
    'miner': 0.1,
    'climber': 0.001,
    'bigfish': 0.01,
    'dodgeball': 0.001,
    'maze': 0.001,
    'leaper': 0.001,
    'fruitbot': 0.001, 
    'bossfight': 0.001,
    'jumper': 0.001,
    'ninja': 0.001,
    'starpilot': 0.001,
    'coinrun': 0.001,
    'heist': 0.001,
    'caveflyer': 0.001,
}

clf_hidden_size = {
    'plunder': 4,
    'chaser': 4,
    'miner': 64,
    'climber': 64,
    'bigfish': 4,
    'dodgeball': 64,
    'maze': 4,
    'leaper': 4,
    'fruitbot': 4, 
    'bossfight': 4,
    'jumper': 4,
    'ninja': 4,
    'starpilot': 4,
    'coinrun': 4,
    'heist': 4,
    'caveflyer': 4,
}

nonlin_envs = ['miner', 'bigfish', 'dodgeball', 'climber']