def __init__(self): self.grid_width = 0.1 self.angle_blockwidth = np.pi / 8 self.env = car_sim_env() self.state_action = [] self.tmp_state_action = [] self.cur_state = None self.cur_action = None
def run(restore, LfD = False): env = car_sim_env() # create environment (also adds some dummy traffic) agt = env.create_agent(LearningAgent, test=False) # create agent env.set_agent(agt, enforce_deadline=True) # specify agent to track train_thread = threading.Thread(name="train", target=train, args=(env, agt, restore, LfD)) train_thread.daemon = True train_thread.start() env.plt_show() while True: continue
def run(restore): env = car_sim_env() agt = env.create_agent(LearningAgent, test=True) env.set_agent(agt, enforce_deadline=False) train_thread = threading.Thread(name="train", target=train, args=(env, agt, restore)) train_thread.daemon = True train_thread.start() env.plt_show() while True: continue
def run(restore): env = car_sim_env() agt = LearningAgent(env, is_test=False) env.set_agent(agt, enforce_deadline=False) #train_thread = threading.Thread(name="train", target=train, args=(env, agt, restore)) #train_thread.daemon = True # exit sub_threading when main_threading is done #train_thread.start() #plt_thread = threading.Thread(name="env.plt_show()", target=env.plt_show(), args=()) #plt_thread.daemon = True #plt_thread.start() env.plt_show() train(env, agt, restore) while True: continue