dagger_lr = LinearRegression(fit_intercept=False)#KernelRidge(kernel='rbf')#
dagger_learner = SKLearner(dagger_lr)
dagger_trajs, dagger_traj_controls, dagger_costs, dagger_avg_costs, dagger_avg_loss, dagger_accs = trials.dagger_trial(dagger_learner, robot, sys)
dagger_final_trajs, dagger_final_controls, dagger_final_costs, dagger_final_avg_costs, dagger_final_avg_loss = trials.dagger_final(dagger_learner, robot, sys)
dagger_data[t, :] = dagger_avg_costs
dagger_loss_data[t, :] = dagger_avg_loss
dagger_final_data[t, :] = dagger_final_avg_costs
dagger_acc_data[t, :] = dagger_accs
# print im_lr.coef_
# print dagger_lr.coef_
# print robot.lqr.K1
vis = Visualizer()
vis.show_trajs(sup_trajs, x_f, "sup_trajs", data_directory)
vis.show_trajs(im_trajs, x_f, "sl_trajs", data_directory)
vis.show_trajs(dagger_trajs, x_f, "dagger_trajs", data_directory)
vis.show_trajs(dagger_final_trajs, x_f, "dagger_final_trajs", data_directory)
print im_accs
print dagger_accs
print "\n\n\n"
for state, control in im_learner.data:
print control
print im_learner.predict(state)
print dagger_learner.predict(state)
state = state.reshape((xdims, 1))
print "\nLearner: "
print learner.estimator.coef_
print "\nLQR: "
print robot.lqr.K
trajs4 = []
for i in range(10):
sys.reset_robot()
states, controls, costs = robot.rollout_learner(learner, verbose=False)
trajs4.append(states)
vis = Visualizer()
vis.show_trajs(trajs1, x_f, "Trajs 1")
vis.show_trajs(trajs2, x_f, "Trajs 2")
vis.show_trajs(trajs3, x_f, "Trajs 3")
vis.show_trajs(trajs4, x_f, "Trajs 4")
"""vis = Visualizer()
vis.set_recording(states)
vis.set_target(x_f)
vis.show()
print "Learner cost: " + str(sum(costs))
"""
#print np.dot(learner.estimator.coef_, init_state)
#print learner.predict(init_state)
