drl-supply-chain-sq-optimization.py

from ax import optimize

def evaluate_sQPolicy(p):
    policy = SQPolicy(
        p['factory_s'], 
        p['factory_Q'],
        [ p['w1_s'], p['w2_s'], p['w3_s'], ],
        [ p['w1_Q'], p['w2_Q'], p['w3_Q'], ]
    )
    return np.mean(simulate(env, policy, num_episodes = 30))

best_parameters, best_values, experiment, model = optimize(
        parameters=[
          { "name": "factory_s",   "type": "range",  "bounds": [0.0, 30.0], },
          { "name": "factory_Q",   "type": "range",  "bounds": [0.0, 30.0], },
          { "name": "w1_s",        "type": "range",  "bounds": [0.0, 20.0], },
          { "name": "w1_Q",        "type": "range",  "bounds": [0.0, 20.0], },  
          { "name": "w2_s",        "type": "range",  "bounds": [0.0, 20.0], },
          { "name": "w2_Q",        "type": "range",  "bounds": [0.0, 20.0], },    
          { "name": "w3_s",        "type": "range",  "bounds": [0.0, 20.0], },
          { "name": "w3_Q",        "type": "range",  "bounds": [0.0, 20.0], },    
        ],
        evaluation_function=evaluate_sQPolicy,
        minimize=False,
        total_trials=200,
    )