def mutate(population):
for individual in population:
mut_p = individual['genome'][-2]
mut_std = individual['genome'][-3]
rand_vals = Initializers.uniform(individual['genome'].shape, mut_std)
for i in range(individual['genome'].shape[0]):
if random.random() < mut_p:
individual['genome'][i] += rand_vals[i]
return population
model.set_tree(tree)
model.set_loss(Losses.MeanSquared())
learning_rate = 0.00002
model.set_optimizer(Optimizers.RMSprop(learning_rate=learning_rate))
# model.compile(X_reward, y_reward)
# model.train(X_reward, y_reward, 24)
reinforce_index = X_obs.shape[0]
X_batches, y_batches, num_batches = ok.make_batches([X_train], y_train, batch_size=10000)
for i in range(8):
print('\n---Iteration {}---'.format(i + 1))
for X_batch, y_batch in zip(X_batches, y_batches):
model.train(X_reward, y_reward, 24)
accuracy, preds = model.get_dream_accuracy([X_batch[0], None], y_batch)
preds = preds[0]
preds += Initializers.normal(preds.shape, 0.01)
print('Accuracy: {}%'.format(accuracy))
preds_reward = reward(preds.reshape(preds.shape[0], preds.shape[1]).astype('float32'),
y_batch.reshape(preds.shape[0], preds.shape[1]).astype('float32'))
print('Avg Reward: {}'.format(np.mean(preds_reward)))
X_reward[0] = np.append(X_reward[0], X_batch[0], axis=0)
X_reward[1] = np.append(X_reward[1], preds, axis=0)
y_reward = np.append(y_reward, preds_reward.reshape(preds_reward.shape[0], 1), axis=0)
params = model.get_params_as_vec()
file = open('reward_model_params_vec.pk', 'wb')
pickle.dump(params, file, protocol=pickle.HIGHEST_PROTOCOL)
file.close()
test_accuracy, test_preds = model.get_dream_accuracy([X_test, None], y_test)
print('Test Accuracy: {}%'.format(test_accuracy))
