def get_config():
M = Model()
dataflow = data_io
from tensorpack.callbacks.base import Callback
class CBSyncWeight(Callback):
def _before_run(self, ctx):
if self.local_step % 10 == 0:
return [M._sync_op_pred]
import functools
from tensorpack.train.config import TrainConfig
from tensorpack.callbacks.saver import ModelSaver
from tensorpack.callbacks.graph import RunOp
from tensorpack.callbacks.param import ScheduledHyperParamSetter, HumanHyperParamSetter, HyperParamSetterWithFunc
from tensorpack.tfutils import sesscreate
from tensorpack.tfutils.common import get_default_sess_config
import tensorpack.tfutils.symbolic_functions as symbf
sigma_beta_steering = symbf.get_scalar_var('actor/sigma_beta_steering',
0.3,
summary=True,
trainable=False)
sigma_beta_accel = symbf.get_scalar_var('actor/sigma_beta_accel',
0.3,
summary=True,
trainable=False)
return TrainConfig(
model=M,
data=dataflow,
callbacks=[
ModelSaver(),
HyperParamSetterWithFunc(
'learning_rate/actor',
functools.partial(M._calc_learning_rate, 'actor')),
HyperParamSetterWithFunc(
'learning_rate/critic',
functools.partial(M._calc_learning_rate, 'critic')),
# ScheduledHyperParamSetter('learning_rate', [(20, 0.0003), (120, 0.0001)]),
ScheduledHyperParamSetter('entropy_beta', [(80, 0.005)]),
# HumanHyperParamSetter('learning_rate'),
# HumanHyperParamSetter('entropy_beta'),
ScheduledHyperParamSetter('actor/sigma_beta_accel', [(1, 0.2),
(2, 0.01)]),
ScheduledHyperParamSetter('actor/sigma_beta_steering',
[(1, 0.1), (2, 0.01)]),
CBSyncWeight(),
data_io,
# PeriodicTrigger(Evaluator(
# EVAL_EPISODE, ['state'], ['policy'], get_player),
# every_k_epochs=3),
] + evaluators,
session_creator=sesscreate.NewSessionCreator(
config=get_default_sess_config(0.5)),
steps_per_epoch=STEPS_PER_EPOCH,
max_epoch=1000,
)
def get_config():
logger.auto_set_dir()
dataset_train, dataset_test = get_data(True), get_data(False)
steps_per_epoch = dataset_train.size() * 5
return TrainConfig(
model=Model(),
data=QueueInput(dataset_train),
callbacks=[
ModelSaver(),
InferenceRunner(dataset_test,
[ScalarStats('cost'), ClassificationError()]),
ScheduledHyperParamSetter('learning_rate', [(200, 1e-4)])
],
session_creator=sesscreate.NewSessionCreator(
config=get_default_sess_config(0.5)),
steps_per_epoch=steps_per_epoch,
max_epoch=500,
)
def get_config():
M = Model()
name_base = str(uuid.uuid1())[:6]
PIPE_DIR = os.environ.get('TENSORPACK_PIPEDIR',
'/tmp/.ipcpipe').rstrip('/')
if not os.path.exists(PIPE_DIR): os.makedirs(PIPE_DIR)
else: os.system('rm -f {}/sim-*'.format(PIPE_DIR))
namec2s = 'ipc://{}/sim-c2s-{}'.format(PIPE_DIR, name_base)
names2c = 'ipc://{}/sim-s2c-{}'.format(PIPE_DIR, name_base)
# AgentTorcs * SIMULATOR_PROC, AgentReplay * SIMULATOR_PROC
procs = [
MySimulatorWorker(k, namec2s, names2c)
for k in range(SIMULATOR_PROC * 2)
]
ensure_proc_terminate(procs)
start_proc_mask_signal(procs)
master = MySimulatorMaster(namec2s, names2c, M)
dataflow = BatchData(DataFromQueue(master.queue), BATCH_SIZE)
class CBSyncWeight(Callback):
def _after_run(self, ctx, _):
if self.local_step > 1 and self.local_step % SIMULATOR_PROC == 0:
# print("before step ",self.local_step)
return [M._td_sync_op]
def _before_run(self, ctx):
if self.local_step % 10 == 0:
return [M._sync_op, M._td_sync_op]
if self.local_step % SIMULATOR_PROC == 0 and 0:
return [M._td_sync_op]
import functools
return TrainConfig(
model=M,
dataflow=dataflow,
callbacks=[
ModelSaver(),
HyperParamSetterWithFunc(
'learning_rate/actor',
functools.partial(M._calc_learning_rate, 'actor')),
HyperParamSetterWithFunc(
'learning_rate/critic',
functools.partial(M._calc_learning_rate, 'critic')),
# ScheduledHyperParamSetter('learning_rate', [(20, 0.0003), (120, 0.0001)]),
ScheduledHyperParamSetter('entropy_beta', [(80, 0.005)]),
# HumanHyperParamSetter('learning_rate'),
# HumanHyperParamSetter('entropy_beta'),
# ScheduledHyperParamSetter('actor/sigma_beta_accel', [(1, 0.2), (2, 0.01), (3, 1e-3), (4, 1e-4)]),
# ScheduledHyperParamSetter('actor/sigma_beta_steering', [(1, 0.1), (2, 0.01), (3, 1e-3), (4, 1e-4)]),
master,
StartProcOrThread(master),
CBSyncWeight(),
# CBTDSyncWeight()
# PeriodicTrigger(Evaluator(
# EVAL_EPISODE, ['state'], ['policy'], get_player),
# every_k_epochs=3),
],
session_creator=sesscreate.NewSessionCreator(
config=get_default_sess_config(0.5)),
steps_per_epoch=STEPS_PER_EPOCH,
max_epoch=1000,
)
