[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

neodroidagent/agents/numpy_agents/model_based/dyna_agent.py

@@ -363,7 +363,7 @@ def _simulate_behavior(self):
             pairs = env_model.state_action_pairs_leading_to_outcome(s_sim)
 
             # add predecessors to queue if their priority exceeds thresh
-            for (_s, _a) in pairs:
+            for _s, _a in pairs:
                 self._update_queue(_s, _a)
 
     def _update(self, s, a):

neodroidagent/agents/numpy_agents/model_free/tabular_q_agent.py

@@ -19,7 +19,6 @@ class TabularQAgent(NumpyAgent):
     # region Private
 
     def __defaults__(self) -> None:
-
         self._action_n = 6
 
         self._init_mean = 0.0
@@ -195,7 +194,6 @@ def _optimise_wrt(self, error, *args, **kwargs) -> None:
         pass
 
     def __build__(self, env, **kwargs) -> None:
-
         if hasattr(self._last_connected_environment.action_space, "num_binary_actions"):
             self._action_n = (
                 self._last_connected_environment.action_space.num_binary_actions

neodroidagent/common/memory/transitions/transitions.py

@@ -88,7 +88,8 @@ def non_terminal_numerical(self):
 @dataclass
 class ValuedTransitionPoint(TransitionPoint):
     """
-    __slots__=['state','action','successor_state','signal','terminal',"distribution","value_estimate"]"""
+    __slots__=['state','action','successor_state','signal','terminal',"distribution","value_estimate"]
+    """
 
     __slots__ = TransitionPoint.__slots__ + ["distribution", "value_estimate"]
     state: Any

neodroidagent/common/session_factory/vertical/procedures/rollout_inference.py

@@ -42,7 +42,6 @@ def __call__(
         :return:"""
         with torch.no_grad():
             with TensorBoardPytorchWriter(log_directory) as metric_writer:
-
                 B = tqdm(count(), f"step {0}, {iterations}", leave=False)
 
                 for _ in B:

neodroidagent/common/session_factory/vertical/procedures/training/experimental/curriculum/curriculum_generation.py

@@ -78,7 +78,6 @@ def main():
             _environment.configure(state=init_state)
             episode_reward = 0
             for k in count(1):
-
                 # actions = _environment.action_space.sample()
                 observations, signal, terminated, info = _environment.sample()
 

neodroidagent/common/session_factory/vertical/procedures/training/off_policy_batched.py

@@ -73,7 +73,6 @@ def __call__(
                 disable=disable_stdout,
                 desc="Step #",
             ):
-
                 sample = self.agent.sample(state)
                 action = self.agent.extract_action(sample)
                 snapshot = self.environment.react(action)

neodroidagent/common/session_factory/vertical/procedures/training/off_policy_step_wise.py

@@ -55,7 +55,6 @@ def __call__(
 
         it = tqdm(range(num_environment_steps), desc="Step #", leave=False)
         for step_i in it:
-
             sample = self.agent.sample(state)
             action = self.agent.extract_action(sample)
 

neodroidagent/common/session_factory/vertical/procedures/training/sampling/rollout.py

@@ -26,7 +26,6 @@ def infer(self, env, render=True):
         state = env.reset()
 
         for frame_i in count(1):
-
             action, *_ = self.sample(state)
             state, signal, terminated, info = env.act(action)
             if render:

neodroidagent/common/session_factory/vertical/single_agent_environment_session.py

@@ -73,7 +73,6 @@ def __call__(
         # with ContextWrapper(torchsnooper.snoop, debug):
         if True:
             with ContextWrapper(torch.autograd.detect_anomaly, debug):
-
                 if agent is None:
                     raise NoAgent
 
@@ -135,7 +134,6 @@ def __call__(
                         drawer_type,
                         not train_agent and drawing_mode != DrawingModeEnum.none,
                     ) as drawer_instance:
-
                         agent.build(
                             self._environment.observation_space,
                             self._environment.action_space,

neodroidagent/entry_points/session_factory.py

@@ -37,7 +37,8 @@ def session_factory(
 ):
     r"""
     Entry point start a starting a training session with the functionality of parsing cmdline arguments and
-    confirming configuration to use before training and overwriting of default training configurations"""
+    confirming configuration to use before training and overwriting of default training configurations
+    """
 
     if config is None:
         config = {}