single_run_epoch_rewards_test.append(run_epoch())
pbar.set_description(
"Avg reward: {:0.6f} | Ewma reward: {:0.6f}".format(
np.mean(single_run_epoch_rewards_test),
utils.ewma(single_run_epoch_rewards_test)))
return single_run_epoch_rewards_test
if __name__ == '__main__':
state_texts = utils.load_data('game.tsv')
dictionary = utils.bag_of_words(state_texts)
state_dim = len(dictionary)
action_dim = NUM_ACTIONS * NUM_OBJECTS
# set up the game
framework.load_game_data()
epoch_rewards_test = [] # shape NUM_RUNS * NUM_EPOCHS
for _ in range(NUM_RUNS):
epoch_rewards_test.append(run())
epoch_rewards_test = np.array(epoch_rewards_test)
x = np.arange(NUM_EPOCHS)
fig, axis = plt.subplots()
axis.plot(x, np.mean(epoch_rewards_test,
axis=0)) # plot reward per epoch averaged per run
axis.set_xlabel('Epochs')
axis.set_ylabel('reward')
axis.set_title(('Linear: nRuns=%d, Epilon=%.2f, Epi=%d, alpha=%.4f' %
optimizer = optim.SGD(model.parameters(), lr=ALPHA)
single_run_epoch_rewards_test = []
pbar = tqdm(range(NUM_EPOCHS), ncols=80)
for _ in pbar:
single_run_epoch_rewards_test.append(run_epoch())
pbar.set_description(
"Avg reward: {:0.6f} | Ewma reward: {:0.6f}".format(
np.mean(single_run_epoch_rewards_test),
utils.ewma(single_run_epoch_rewards_test)))
return single_run_epoch_rewards_test
if __name__ == '__main__':
pass
'''
state_texts = utils.load_data('game.tsv')
dictionary = utils.bag_of_words(state_texts)
framework.load_game_data()
'''
state_dim = K * 3 + 1
action_dim = NUM_ACTIONS
# set up the game
game = framework.NewsVendorGame(K, Kpr, Kst, Kpe, Ktr, CWarehouse, CTruck,
Price, dmax)
epoch_rewards_test = [] # shape NUM_RUNS * NUM_EPOCHS
for _ in range(NUM_RUNS):