}
info = "TDQ" + "_L" + str(self.env.lanes) + "-R" + str(self.env.rows)
super().save_model(path, info)
# Example of usage
if __name__ == '__main__':
np.random.seed(0)
loggingBase = LoggingBase()
module_path = loggingBase.module_path
env = RoRoDeck(lanes=10, rows=12)
number_of_episodes = 5000
agent = TDQLearning(env=env,
module_path=module_path,
number_of_episodes=number_of_episodes)
model, total_rewards, steps_to_exit, eps_history, state_expansion = agent.train(
)
plotter = Plotter(module_path, agent.number_of_episodes, show_plot=True)
plotter.plotRewardPlot(total_rewards)
plotter.plotStateExp(state_expansion)
plotter.plotEPSHistory(np.array(eps_history))
plotter.plot_cargo_units_loaded(np.array(steps_to_exit))
evaluator = Evaluator(env.vehicle_data, env.grid)
evaluation = evaluator.evaluate(env.get_stowage_plan())
print(evaluation)
def test_shifts():
random_actions_1 = [
0, 3, 3, 0, 3, 0, 2, 1, 0, 4, 0, 3, 4, 4, 1, 0, 2, 4, 4, 2, 4, 3, 2, 3,
0, 0, 0, 3, 4, 4, 2, 2, 4, 1, 3, 3, 3, 1, 2, 2, 3, 2, 3, 4, 4, 2, 1, 2,
0, 3, 0, 2, 4, 3, 2, 1, 2, 1, 4, 1, 0, 0, 0, 0, 0, 1, 0, 3, 1, 4, 1, 2,
4, 0, 0, 2, 0, 4, 4, 4, 1, 1, 4, 1, 1, 3, 1, 3, 3, 1, 1, 1, 0, 3, 0, 4,
1, 4, 0, 3
]
random_actions_2 = [
0, 3, 3, 0, 3, 0, 2, 1, 0, 4, 0, 3, 4, 4, 1, 0, 2, 4, 4, 2, 4, 3, 2, 3,
0, 0, 0, 3, 4, 4, 2, 2, 4, 1, 3, 3, 3, 1, 2, 2, 3, 2, 3, 4, 4, 2, 1, 2,
0, 3, 0, 2, 4, 3, 2, 1, 2, 1, 4, 1, 0, 0, 0, 0, 0, 1, 0, 3, 1, 4, 1, 2,
4, 0, 0, 2, 0, 4, 4, 4, 1, 1, 4, 1, 1, 3, 1, 3, 3, 1, 1, 1, 0, 3, 0, 4,
1, 4, 0, 3
]
random_actions_3 = [
0, 3, 3, 0, 3, 0, 2, 1, 0, 4, 0, 3, 4, 4, 1, 0, 2, 4, 4, 2, 4, 3, 2, 3,
0, 0, 0, 3, 0, 3, 3, 0, 3, 0, 2, 1, 0, 4, 0, 3, 4, 4, 1, 0, 2, 4, 4, 2,
4, 3, 2, 3, 0, 0, 0, 3, 2, 1, 4, 1, 0, 0, 0, 0, 0, 1, 0, 3, 1, 4, 1, 2,
4, 0, 0, 2, 0, 4, 4, 4, 1, 1, 4, 1, 4, 4, 2, 2, 4, 1, 3, 3, 3, 1, 2, 2,
4, 1, 2, 4, 0, 0, 2, 0, 4, 4, 4, 1, 1, 4, 1, 4, 1, 3, 1, 3, 3, 1, 1, 1,
0, 3, 0, 4, 1, 4, 0, 3, 2, 4
]
i = 0
env1.reset()
done_ = False
while not done_:
action_ = random_actions_1[i]
_, _, done_, _ = env1.step(action_)
i += 1
i = 0
env2.reset()
done_ = False
while not done_:
action_ = random_actions_2[i]
_, _, done_, _ = env2.step(action_)
i += 1
env3 = RoRoDeck(lanes=8, rows=20)
env3.reset()
i = 0
done_ = False
while not done_:
action_ = random_actions_3[i % len(random_actions_3)]
_, _, done_, _ = env3.step(action_)
i += 1
evaluator1 = Evaluator(env1.vehicle_data, env1.grid)
shifts1 = evaluator1.evaluate(env1.get_stowage_plan()).shifts
evaluator2 = Evaluator(env2.vehicle_data, env2.grid)
shifts2 = evaluator2.evaluate(env2.get_stowage_plan()).shifts
evaluator3 = Evaluator(env3.vehicle_data, env3.grid)
shifts3 = evaluator3.evaluate(env3.get_stowage_plan()).shifts
assert shifts1 == 3
assert shifts2 == 3
assert shifts3 == 19