class Walker:
def __init__(self, n_features, n_actions):
self.n_features = n_features
self.n_actions = n_actions
# env, simulate observations
env = open('env_hole.pkl', 'rb')
self.observe_env = pickle.load(env)
env.close()
env = open('env_hole_vol.pkl', 'rb')
self.observe_vol = pickle.load(env)
env.close()
# current position
self.pos_x = None
self.pos_y = 1.0
self.pos_z = None
# 8 action dim
self.action_labels = [
'0', '45', '90', '135', '180', '225', '270', '315'
]
self.actor = Actor(self.n_features, self.n_actions, lr=0.004)
self.actor.load_trained_model("save/multiple/hole/save100.ckpt")
# fixme, first define critic before load : will report bug for not found in checkpoint
self.critic = Critic(self.n_features,
self.n_actions,
lr=0.003,
gamma=0.95)
# fixme, use trained model to predict
self.bin_graph = tf.Graph()
with self.bin_graph.as_default():
self.bin_classfic = BinSupervisor(366, 2)
# fixme, avoid obstacles, env defined in A star
self.astar = Astar()
def reset_walker_pos(self, x, y, z):
self.pos_x = x
self.pos_y = y
self.pos_z = z
# '-2.0_1_2.0':[gcc_vector, label]
def observe_gcc_vector(self, x, y, z):
# pick as key
key = str(float(x)) + "_" + str(y) + "_" + str(float(z))
return self.observe_env[key][0]
# '-2.0_1_2.0':vol
def observe_volume(self, x, y, z):
# return is a 4-dim vector for each mic
key = str(float(x)) + "_" + str(y) + "_" + str(float(z))
return self.observe_vol[key]
def choose_action(self, s, invalid_actions):
a, p = self.actor.output_action(s, invalid_actions)
return a, p
def learn(self, s, a, s_, r):
td = self.critic.learn(s, r, s_)
self.actor.learn(s, a, td)
# fixme, call binary model to judge in room or not
# use argmax to determine
def sound_in_room(self, x):
with self.bin_graph.as_default():
acts = self.bin_classfic.is_in_room(x)
if np.argmax(acts) == 0:
return True
else:
return False
def find_shortest_path(self, sx, sz, dx, dz):
return self.astar.find_path(sx, sz, dx, dz)
