else:
replay_buffer = ReplayBuffer(args.replay_buffer_size)
U.initialize()
update_target()
num_iters = 0
# Load the model
state = maybe_load_model(savedir, container)
if state is not None:
num_iters, replay_buffer = state["num_iters"], state[
"replay_buffer"],
monitored_env.set_state(state["monitor_state"])
start_time, start_steps = None, None
steps_per_iter = RunningAvg(0.999)
iteration_time_est = RunningAvg(0.999)
obs = env.reset()
# Record the mean of the \sigma
sigma_name_list = []
sigma_list = []
for param in tf.trainable_variables():
# only record the \sigma in the action network
if 'sigma' in param.name \
and 'deepq/q_func/action_value' in param.name:
summary_name = \
param.name.replace(
'deepq/q_func/action_value/', '').replace(
'/', '.').split(':')[0]
sigma_name_list.append(summary_name)
sigma_list.append(tf.reduce_mean(tf.abs(param)))
else:
replay_buffer = ReplayBuffer(args.replay_buffer_size)
U.initialize()
update_target()
num_iters = 0
# Load the model
state = maybe_load_model(savedir, container)
if state is not None:
num_iters, replay_buffer = state["num_iters"], state[
"replay_buffer"],
monitored_env.set_state(state["monitor_state"])
start_time, start_steps = None, None
steps_per_iter = RunningAvg(0.999)
iteration_time_est = RunningAvg(0.999)
obs = env.reset()
# Record the mean of the \sigma
sigma_name_list = []
sigma_list = []
for param in tf.trainable_variables():
# only record the \sigma in the action network
if 'sigma' in param.name \
and 'deepq/q_func/action_value' in param.name:
summary_name = \
param.name.replace(
'deepq/q_func/action_value/', '').replace(
'/', '.').split(':')[0]
sigma_name_list.append(summary_name)
sigma_list.append(tf.reduce_mean(tf.abs(param)))