control.reinforcement_learning package

Subpackages

• control.reinforcement_learning.DQN package
  • Submodules
  • control.reinforcement_learning.DQN.Agent module
    • Agent
      • Agent.evaluate_model()
      • Agent.parse_ini()
      • Agent.plot_value_policy()
      • Agent.policy()
      • Agent.save_metrics()
      • Agent.train()
      • Agent.train_model()
  • control.reinforcement_learning.DQN.DeepQNetwork module
    • DeepQNetwork
      • DeepQNetwork.evaluate()
      • DeepQNetwork.predict()
      • DeepQNetwork.train_batch_gradientTape()
      • DeepQNetwork.train_on_batch()
  • control.reinforcement_learning.DQN.ReplayBuffer module
    • ReplayBuffer
      • ReplayBuffer.sample_batch()
      • ReplayBuffer.store_tuple()
  • Module contents
• control.reinforcement_learning.Environments package
  • Submodules
  • control.reinforcement_learning.Environments.FakeEnv module
    • FakeEnv
      • FakeEnv.render()
      • FakeEnv.reset()
      • FakeEnv.step()
  • control.reinforcement_learning.Environments.PyBulletPendulumEnv module
    • PyBulletPendulumEnv
      • PyBulletPendulumEnv.action_space
      • PyBulletPendulumEnv.calculate_reward()
      • PyBulletPendulumEnv.close()
      • PyBulletPendulumEnv.get_state()
      • PyBulletPendulumEnv.load_pendulum_urdf()
      • PyBulletPendulumEnv.metadata
      • PyBulletPendulumEnv.observation_space
      • PyBulletPendulumEnv.render()
      • PyBulletPendulumEnv.reset()
      • PyBulletPendulumEnv.reset_policy()
      • PyBulletPendulumEnv.reset_robot()
      • PyBulletPendulumEnv.send_fake_serial()
      • PyBulletPendulumEnv.step()
  • control.reinforcement_learning.Environments.RealPendulumEnv module
    • RealPendulumEnv
      • RealPendulumEnv.action_space
      • RealPendulumEnv.calculate_reward()
      • RealPendulumEnv.close()
      • RealPendulumEnv.metadata
      • RealPendulumEnv.observation_space
      • RealPendulumEnv.render()
      • RealPendulumEnv.reset()
      • RealPendulumEnv.reset_policy()
      • RealPendulumEnv.send_serial()
      • RealPendulumEnv.step()
  • control.reinforcement_learning.Environments.SerialReader module
    • SerialReader
      • SerialReader.get_state()
      • SerialReader.read_serial()
      • SerialReader.run()
  • Module contents

Module contents