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

pre-commit-ci[bot] · pre-commit-ci[bot] · commit f5f99dcf386d · 2024-10-28T21:11:09.000Z
for more information, see https://pre-commit.ci
diff --git a/examples/demo_agents/video_plot_a2c.py b/examples/demo_agents/video_plot_a2c.py
@@ -9,6 +9,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_a2c.jpg'
 
 from rlberry_research.agents.torch import A2CAgent
diff --git a/examples/demo_agents/video_plot_mbqvi.py b/examples/demo_agents/video_plot_mbqvi.py
@@ -9,6 +9,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_mbqvi.jpg'
 from rlberry_scool.agents.mbqvi import MBQVIAgent
 from rlberry_research.envs.finite import GridWorld
diff --git a/examples/demo_agents/video_plot_ppo.py b/examples/demo_agents/video_plot_ppo.py
@@ -9,6 +9,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_a2c.jpg'
 
 from rlberry_research.agents.torch import PPOAgent
diff --git a/examples/demo_agents/video_plot_rs_kernel_ucbvi.py b/examples/demo_agents/video_plot_rs_kernel_ucbvi.py
@@ -9,6 +9,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_rs_kernel_ucbvi.jpg'
 
 from rlberry_research.envs import Acrobot
diff --git a/examples/demo_agents/video_plot_rsucbvi.py b/examples/demo_agents/video_plot_rsucbvi.py
@@ -9,6 +9,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_rsucbvi.jpg'
 
 from rlberry_research.agents import RSUCBVIAgent
diff --git a/examples/demo_agents/video_plot_vi.py b/examples/demo_agents/video_plot_vi.py
@@ -9,6 +9,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_vi.jpg'
 
 from rlberry_scool.agents.dynprog import ValueIterationAgent
diff --git a/examples/demo_bandits/plot_compare_index_bandits.py b/examples/demo_bandits/plot_compare_index_bandits.py
@@ -6,6 +6,7 @@
 This script Compare several bandits agents and as a sub-product also shows
 how to use subplots in with `plot_writer_data`
 """
+
 import numpy as np
 import matplotlib.pyplot as plt
 from rlberry_research.envs.bandits import BernoulliBandit
diff --git a/examples/demo_bandits/plot_mirror_bandit.py b/examples/demo_bandits/plot_mirror_bandit.py
@@ -12,6 +12,7 @@
 The code is in three parts: definition of environment, definition of agent,
 and finally definition of the experiment.
 """
+
 import numpy as np
 
 from rlberry.manager import ExperimentManager, read_writer_data
diff --git a/examples/demo_env/example_atari_atlantis_vectorized_ppo.py b/examples/demo_env/example_atari_atlantis_vectorized_ppo.py
@@ -11,6 +11,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/example_plot_atari_atlantis_vectorized_ppo.jpg'
 
 
diff --git a/examples/demo_env/example_atari_breakout_vectorized_ppo.py b/examples/demo_env/example_atari_breakout_vectorized_ppo.py
@@ -11,6 +11,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/example_plot_atari_breakout_vectorized_ppo.jpg'
 
 
diff --git a/examples/demo_env/video_plot_acrobot.py b/examples/demo_env/video_plot_acrobot.py
@@ -9,6 +9,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_acrobot.jpg'
 
 from rlberry_research.envs import Acrobot
diff --git a/examples/demo_env/video_plot_apple_gold.py b/examples/demo_env/video_plot_apple_gold.py
@@ -9,6 +9,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_apple_gold.jpg'
 from rlberry_research.envs.benchmarks.grid_exploration.apple_gold import AppleGold
 from rlberry_scool.agents.dynprog import ValueIterationAgent
diff --git a/examples/demo_env/video_plot_atari_freeway.py b/examples/demo_env/video_plot_atari_freeway.py
@@ -11,6 +11,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_atari_freeway.jpg'
 
 
diff --git a/examples/demo_env/video_plot_chain.py b/examples/demo_env/video_plot_chain.py
@@ -8,6 +8,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_chain.jpg'
 
 
diff --git a/examples/demo_env/video_plot_gridworld.py b/examples/demo_env/video_plot_gridworld.py
@@ -10,6 +10,7 @@
 .. video:: ../../video_plot_gridworld.mp4
    :width: 600
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_gridworld.jpg'
 
 from rlberry_scool.agents.dynprog import ValueIterationAgent
diff --git a/examples/demo_env/video_plot_mountain_car.py b/examples/demo_env/video_plot_mountain_car.py
@@ -8,6 +8,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_montain_car.jpg'
 
 from rlberry_scool.agents.mbqvi import MBQVIAgent
diff --git a/examples/demo_env/video_plot_old_gym_compatibility_wrapper_old_acrobot.py b/examples/demo_env/video_plot_old_gym_compatibility_wrapper_old_acrobot.py
@@ -8,6 +8,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_old_gym_acrobot.jpg'
 
 
diff --git a/examples/demo_env/video_plot_pball.py b/examples/demo_env/video_plot_pball.py
@@ -8,6 +8,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_pball.jpg'
 
 import numpy as np
diff --git a/examples/demo_env/video_plot_rooms.py b/examples/demo_env/video_plot_rooms.py
@@ -8,6 +8,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_rooms.jpg'
 
 from rlberry_research.envs.benchmarks.grid_exploration.nroom import NRoom
diff --git a/examples/demo_env/video_plot_springcartpole.py b/examples/demo_env/video_plot_springcartpole.py
@@ -11,6 +11,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_springcartpole.jpg'
 
 from rlberry_research.envs.classic_control import SpringCartPole
diff --git a/examples/demo_env/video_plot_twinrooms.py b/examples/demo_env/video_plot_twinrooms.py
@@ -8,6 +8,7 @@
    :width: 600
 
 """
+
 # sphinx_gallery_thumbnail_path = 'thumbnails/video_plot_twinrooms.jpg'
 
 from rlberry_research.envs.benchmarks.generalization.twinrooms import TwinRooms
diff --git a/examples/example_venv.py b/examples/example_venv.py
@@ -13,7 +13,6 @@
 and are only there to give the script's text.
 """
 
-
 from rlberry.manager import with_venv, run_venv_xp
 
 
diff --git a/examples/plot_checkpointing.py b/examples/plot_checkpointing.py
@@ -8,6 +8,7 @@
 This is a minimal example of how to create checkpoints while training
 your agents, and how to restore from a previous checkpoint.
 """
+
 from rlberry.agents import Agent
 from rlberry.manager import ExperimentManager
 from rlberry.manager import plot_writer_data
diff --git a/examples/plot_writer_wrapper.py b/examples/plot_writer_wrapper.py
@@ -19,7 +19,6 @@
     `rlberry.manager.plot_writer_data` documentation for more information.
 """
 
-
 import numpy as np
 
 from rlberry_scool.envs import GridWorld
diff --git a/rlberry/rendering/render_interface.py b/rlberry/rendering/render_interface.py
@@ -2,7 +2,6 @@
 Interface that allows 2D rendering.
 """
 
-
 from abc import ABC, abstractmethod
 
 from rlberry.rendering.opengl_render2d import OpenGLRender2D
diff --git a/rlberry/tests/test_agents_base.py b/rlberry/tests/test_agents_base.py
@@ -6,7 +6,6 @@
 
 """
 
-
 import pytest
 import numpy as np
 import sys
diff --git a/rlberry/wrappers/tests/old_env/old_acrobot.py b/rlberry/wrappers/tests/old_env/old_acrobot.py
@@ -219,10 +219,7 @@ def _dsdt(self, s_augmented, t):
             # the following line is consistent with the java implementation
             # and the book
             ddtheta2 = (
-                a
-                + d2 / d1 * phi1
-                - m2 * l1 * lc2 * dtheta1**2 * np.sin(theta2)
-                - phi2
+                a + d2 / d1 * phi1 - m2 * l1 * lc2 * dtheta1**2 * np.sin(theta2) - phi2
             ) / (m2 * lc2**2 + I2 - d2**2 / d1)
         ddtheta1 = -(d2 * ddtheta2 + phi1) / d1
         return (dtheta1, dtheta2, ddtheta1, ddtheta2, 0.0)
diff --git a/rlberry/wrappers/tests/old_env/old_pendulum.py b/rlberry/wrappers/tests/old_env/old_pendulum.py
@@ -82,9 +82,7 @@ def step(self, action):
 
         action = np.clip(action, -self.max_torque, self.max_torque)[0]
         self.last_action = action  # for rendering
-        costs = (
-            angle_normalize(theta) ** 2 + 0.1 * thetadot**2 + 0.001 * (action**2)
-        )
+        costs = angle_normalize(theta) ** 2 + 0.1 * thetadot**2 + 0.001 * (action**2)
 
         # compute the next state after action
         newthetadot = (
diff --git a/scripts/fetch_contributors.py b/scripts/fetch_contributors.py
@@ -4,6 +4,7 @@
 The table should be updated for each new inclusion in the teams.
 Generating the table requires admin rights.
 """
+
 import requests
 import time
 from pathlib import Path
