def bellman_test_features(args): if args.model != 'bellman': raise Exception, 'wrong model for this' (feature_fn, margin_fn, num_features, actions) = select_feature_fn(args) demofile = h5py.File(args.demofile, 'r') # get a random set of trajectories trajectories = [] traj = [] for uid in range(len(demofile)): key = str(uid) group = demofile[key] state = [key,group['cloud_xyz'][:]] # these are already downsampled action = group['action'][()] if not group['knot'][()] else 'done' if group['pred'][()] == key: if traj: trajectories.append(traj) traj = [] traj.append([state, action]) if traj: trajectories.append(traj) random.shuffle(trajectories) constraint_trajs = trajectories[:args.num_constraints] # put them into a Bellman model mm_model = BellmanMaxMarginModel(action, 500, 1000, 10, .9, num_features, feature_fn, margin_fn) for i, t in enumerate(constraint_trajs): mm_model.add_trajectory(t, str(i), True) weights, w0 = mm_model.optimize_model() # evaluate value fn performance num_evals = len(trajectories) if args.num_evals < 0 else args.num_constraints + args.num_evals trajectories = trajectories[args.num_constraints:num_evals] values = np.zeros((len(trajectories), 6)) num_decreases = 0 for (i, t) in enumerate(trajectories): for j, (s, a) in enumerate(t): values[i, j] = np.dot(mm_model.weights, mm_model.feature_fn(s, a)) for k in range(j): if values[i, k] > values[i, k+1]: num_decreases += 1 print "DECREASE", values[i, k], values[i, k+1] sys.stdout.write('num decreases:\t{} computed values for trajectory {}\r'.format(num_decreases, i)) sys.stdout.flush() sys.stdout.write('\n') print "num decreases:\t", num_decreases ipy.embed()