time_of_start = time.time()
# set the title of the terminal so that what the terminal is doing is clear
print('\33]0;{}\a'.format(' '.join(sys.argv)), end='', flush=True)
print(args)
# compile the simulation module in C
check_C_module_and_compile()
# set the replay memory
capacity = round(args.size_of_replay_memory * controls_per_half_period *
t_max) if args.train else 1
memory = RL.Memory(capacity = capacity, data_size = data_size * 2 + 2 if args.input != 'measurements' else \
(read_control_step_length+read_length) + read_length//read_control_step_length+1 + 2,
policy = 'random', passes_before_random = 0.2)
# define the neural network
net = RL.direct_DQN(data_size).cuda(
) if args.input != 'measurements' else RL.DQN_measurement(read_length)
# set the task
if args.train or args.LQG:
train = RL.TrainDQN(net,
memory,
batch_size=args.batch_size,
gamma=0.99,
backup_period=args.target_network_update_interval,
args=args)
del net
# the main function of training
if args.train:
main = Main_System(train, num_of_processes=args.num_of_actors)
main(num_of_episodes)
# when we do not train and we test the result of LQG
elif args.LQG:
# set the title of the terminal so that what the terminal is doing is clear
print('\33]0;{}\a'.format(' '.join(sys.argv)), end='', flush=True)
print(args)
# compile the simulation module in C
check_C_module_and_compile()
# set the replay memory
capacity = round(args.size_of_replay_memory * controls_per_unit_time *
t_max) if args.train else 1
memory = RL.Memory(capacity=capacity,
data_size=data_size * 2 + 2,
policy='random',
passes_before_random=0.2)
# define the neural network
net = RL.direct_DQN(data_size).cuda()
# set the task
if args.train or args.control_strategy != 'DQN':
train = RL.TrainDQN(net,
memory,
batch_size=args.batch_size,
gamma=0.99,
backup_period=args.target_network_update_interval,
args=args)
del net
# the main function of training
if args.train:
main = Main_System(train, num_of_processes=args.num_of_actors)
main(num_of_episodes)
# when we do not train and we test the result of analytic strategies
elif args.control_strategy != 'DQN':
