saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-07-28 20:11:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

reverted generic offpolicy

Browse source
This commit is contained in:
Stelios Tymvios 2020-07-10 11:27:51 +03:00
parent 641a330732
commit e317ba694f
2 changed files with 3 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
stable_baselines3/common/off_policy_algorithm.py
View file

@ -19,10 +19,8 @@ from stable_baselines3.common.noise import ActionNoise
from stable_baselines3.common.buffers import ReplayBuffer
from stable_baselines3.common.save_util import save_to_pkl, load_from_pkl
_BufferType = TypeVar("_BufferType", bound=ReplayBuffer)
class OffPolicyAlgorithm(BaseAlgorithm, Generic[_BufferType]):
class OffPolicyAlgorithm(BaseAlgorithm):
"""
The base for Off-Policy algorithms (ex: SAC/TD3)
@ -75,7 +73,7 @@ class OffPolicyAlgorithm(BaseAlgorithm, Generic[_BufferType]):
env: Union[GymEnv, str],
policy_base: Type[BasePolicy],
learning_rate: Union[float, Callable],
replay_buffer_cls: Type[_BufferType] = None,
replay_buffer_cls: Type[ReplayBuffer] = None,
replay_buffer_kwargs: Optional[Mapping[str, Any]] = None,
buffer_size: int = int(1e6),
learning_starts: int = 100,

2
tests/test_buffers.py
View file

@ -101,4 +101,4 @@ def test_with_algo(algo):
agent.replay_buffer_cls = NstepReplayBuffer
agent.replay_buffer_kwargs.update({"gamma":agent.gamma, "n_step": 10})
agent._setup_model()
agent.learn(500)
agent.learn(500)