Disable n-step replay
This commit is contained in:
parent
672cb256b1
commit
5217a0bd73
|
|
@ -3,7 +3,6 @@ from typing import Any, Callable, Dict, List, Optional, Tuple, Type, Union
|
||||||
import numpy as np
|
import numpy as np
|
||||||
import torch as th
|
import torch as th
|
||||||
from stable_baselines3.common import logger
|
from stable_baselines3.common import logger
|
||||||
from stable_baselines3.common.buffers import ReplayBuffer
|
|
||||||
from stable_baselines3.common.noise import ActionNoise
|
from stable_baselines3.common.noise import ActionNoise
|
||||||
from stable_baselines3.common.off_policy_algorithm import OffPolicyAlgorithm
|
from stable_baselines3.common.off_policy_algorithm import OffPolicyAlgorithm
|
||||||
from stable_baselines3.common.type_aliases import GymEnv, MaybeCallback
|
from stable_baselines3.common.type_aliases import GymEnv, MaybeCallback
|
||||||
|
|
@ -75,8 +74,6 @@ class TQC(OffPolicyAlgorithm):
|
||||||
n_episodes_rollout: int = -1,
|
n_episodes_rollout: int = -1,
|
||||||
action_noise: Optional[ActionNoise] = None,
|
action_noise: Optional[ActionNoise] = None,
|
||||||
optimize_memory_usage: bool = False,
|
optimize_memory_usage: bool = False,
|
||||||
replay_buffer_class: Optional[Type[ReplayBuffer]] = None,
|
|
||||||
replay_buffer_kwargs: Optional[Dict[str, Any]] = None,
|
|
||||||
ent_coef: Union[str, float] = "auto",
|
ent_coef: Union[str, float] = "auto",
|
||||||
target_update_interval: int = 1,
|
target_update_interval: int = 1,
|
||||||
target_entropy: Union[str, float] = "auto",
|
target_entropy: Union[str, float] = "auto",
|
||||||
|
|
@ -98,8 +95,6 @@ class TQC(OffPolicyAlgorithm):
|
||||||
env,
|
env,
|
||||||
TQCPolicy,
|
TQCPolicy,
|
||||||
learning_rate,
|
learning_rate,
|
||||||
replay_buffer_class,
|
|
||||||
replay_buffer_kwargs,
|
|
||||||
buffer_size,
|
buffer_size,
|
||||||
learning_starts,
|
learning_starts,
|
||||||
batch_size,
|
batch_size,
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue