Fixed: Upgrade changing interfaces
This commit is contained in:
parent
f3e03916c8
commit
844cdb1319
@ -134,31 +134,31 @@ class SAC(OffPolicyAlgorithm):
|
|||||||
_init_setup_model: bool = True,
|
_init_setup_model: bool = True,
|
||||||
):
|
):
|
||||||
super().__init__(
|
super().__init__(
|
||||||
policy,
|
policy=policy,
|
||||||
env,
|
env=env,
|
||||||
None, # PolicyBase
|
learning_rate=learning_rate,
|
||||||
learning_rate,
|
buffer_size=buffer_size,
|
||||||
buffer_size,
|
learning_starts=learning_starts,
|
||||||
learning_starts,
|
batch_size=batch_size,
|
||||||
batch_size,
|
tau=tau,
|
||||||
tau,
|
gamma=gamma,
|
||||||
gamma,
|
train_freq=train_freq,
|
||||||
train_freq,
|
gradient_steps=gradient_steps,
|
||||||
gradient_steps,
|
action_noise=action_noise,
|
||||||
action_noise,
|
|
||||||
replay_buffer_class=replay_buffer_class,
|
replay_buffer_class=replay_buffer_class,
|
||||||
replay_buffer_kwargs=replay_buffer_kwargs,
|
replay_buffer_kwargs=replay_buffer_kwargs,
|
||||||
policy_kwargs=policy_kwargs,
|
policy_kwargs=policy_kwargs,
|
||||||
tensorboard_log=tensorboard_log,
|
tensorboard_log=tensorboard_log,
|
||||||
verbose=verbose,
|
verbose=verbose,
|
||||||
device=device,
|
device=device,
|
||||||
|
support_multi_env=False,
|
||||||
|
monitor_wrapper=True,
|
||||||
seed=seed,
|
seed=seed,
|
||||||
use_sde=use_sde,
|
use_sde=use_sde,
|
||||||
sde_sample_freq=sde_sample_freq,
|
sde_sample_freq=sde_sample_freq,
|
||||||
use_sde_at_warmup=use_sde_at_warmup,
|
use_sde_at_warmup=use_sde_at_warmup,
|
||||||
optimize_memory_usage=optimize_memory_usage,
|
sde_support=True,
|
||||||
supported_action_spaces=(gym.spaces.Box),
|
supported_action_spaces=(gym.spaces.Box),
|
||||||
support_multi_env=True,
|
|
||||||
)
|
)
|
||||||
|
|
||||||
self.target_entropy = target_entropy
|
self.target_entropy = target_entropy
|
||||||
|
Loading…
Reference in New Issue
Block a user