Index

A

action_space (control.reinforcement_learning.Environments.PyBulletPendulumEnv.PyBulletPendulumEnv attribute) (control.reinforcement_learning.Environments.RealPendulumEnv.RealPendulumEnv attribute)

Agent (class in control.reinforcement_learning.DQN.Agent)

C

calculate_bar_mass() (control.pid.classes.EnergyController.EnergyController method) calculate_polar_inertia() (control.pid.classes.EnergyController.EnergyController method) calculate_reward() (control.reinforcement_learning.Environments.PyBulletPendulumEnv.PyBulletPendulumEnv method) (control.reinforcement_learning.Environments.RealPendulumEnv.RealPendulumEnv method) close() (control.reinforcement_learning.Environments.PyBulletPendulumEnv.PyBulletPendulumEnv method) (control.reinforcement_learning.Environments.RealPendulumEnv.RealPendulumEnv method) compute() (control.pid.classes.PIDController.PIDController method) control module control() (control.pid.classes.EnergyController.EnergyController method) control.optimal_control module control.optimal_control.mpc module control.pid module control.pid.classes module control.pid.classes.EnergyController module control.pid.classes.PIDController module

control.reinforcement_learning module control.reinforcement_learning.DQN module control.reinforcement_learning.DQN.Agent module control.reinforcement_learning.DQN.DeepQNetwork module control.reinforcement_learning.DQN.ReplayBuffer module control.reinforcement_learning.Environments module control.reinforcement_learning.Environments.FakeEnv module control.reinforcement_learning.Environments.PyBulletPendulumEnv module control.reinforcement_learning.Environments.RealPendulumEnv module control.reinforcement_learning.Environments.SerialReader module

D

DeepQNetwork (class in control.reinforcement_learning.DQN.DeepQNetwork)

E

EnergyController (class in control.pid.classes.EnergyController)

evaluate() (control.reinforcement_learning.DQN.DeepQNetwork.DeepQNetwork method) evaluate_model() (control.reinforcement_learning.DQN.Agent.Agent method)

F

FakeEnv (class in control.reinforcement_learning.Environments.FakeEnv)

G

get_state() (control.reinforcement_learning.Environments.PyBulletPendulumEnv.PyBulletPendulumEnv method) (control.reinforcement_learning.Environments.SerialReader.SerialReader method)

L

load_pendulum_urdf() (control.reinforcement_learning.Environments.PyBulletPendulumEnv.PyBulletPendulumEnv method)

M

metadata (control.reinforcement_learning.Environments.PyBulletPendulumEnv.PyBulletPendulumEnv attribute) (control.reinforcement_learning.Environments.RealPendulumEnv.RealPendulumEnv attribute) module control control.optimal_control control.optimal_control.mpc control.pid control.pid.classes control.pid.classes.EnergyController control.pid.classes.PIDController control.reinforcement_learning control.reinforcement_learning.DQN control.reinforcement_learning.DQN.Agent control.reinforcement_learning.DQN.DeepQNetwork control.reinforcement_learning.DQN.ReplayBuffer control.reinforcement_learning.Environments control.reinforcement_learning.Environments.FakeEnv control.reinforcement_learning.Environments.PyBulletPendulumEnv control.reinforcement_learning.Environments.RealPendulumEnv control.reinforcement_learning.Environments.SerialReader

O

observation_space (control.reinforcement_learning.Environments.PyBulletPendulumEnv.PyBulletPendulumEnv attribute) (control.reinforcement_learning.Environments.RealPendulumEnv.RealPendulumEnv attribute)

P

parse_ini() (control.reinforcement_learning.DQN.Agent.Agent method) PIDController (class in control.pid.classes.PIDController) plot_value_policy() (control.reinforcement_learning.DQN.Agent.Agent method)

policy() (control.reinforcement_learning.DQN.Agent.Agent method) predict() (control.reinforcement_learning.DQN.DeepQNetwork.DeepQNetwork method) PyBulletPendulumEnv (class in control.reinforcement_learning.Environments.PyBulletPendulumEnv)

R

read_serial() (control.reinforcement_learning.Environments.SerialReader.SerialReader method) RealPendulumEnv (class in control.reinforcement_learning.Environments.RealPendulumEnv) render() (control.reinforcement_learning.Environments.FakeEnv.FakeEnv method) (control.reinforcement_learning.Environments.PyBulletPendulumEnv.PyBulletPendulumEnv method) (control.reinforcement_learning.Environments.RealPendulumEnv.RealPendulumEnv method) ReplayBuffer (class in control.reinforcement_learning.DQN.ReplayBuffer) reset() (control.pid.classes.EnergyController.EnergyController method) (control.pid.classes.PIDController.PIDController method) (control.reinforcement_learning.Environments.FakeEnv.FakeEnv method) (control.reinforcement_learning.Environments.PyBulletPendulumEnv.PyBulletPendulumEnv method) (control.reinforcement_learning.Environments.RealPendulumEnv.RealPendulumEnv method)

reset_policy() (control.reinforcement_learning.Environments.PyBulletPendulumEnv.PyBulletPendulumEnv method) (control.reinforcement_learning.Environments.RealPendulumEnv.RealPendulumEnv method) reset_robot() (control.reinforcement_learning.Environments.PyBulletPendulumEnv.PyBulletPendulumEnv method) run() (control.reinforcement_learning.Environments.SerialReader.SerialReader method)

S

sample_batch() (control.reinforcement_learning.DQN.ReplayBuffer.ReplayBuffer method) save_metrics() (control.reinforcement_learning.DQN.Agent.Agent method) send_fake_serial() (control.reinforcement_learning.Environments.PyBulletPendulumEnv.PyBulletPendulumEnv method) send_serial() (control.reinforcement_learning.Environments.RealPendulumEnv.RealPendulumEnv method)

SerialReader (class in control.reinforcement_learning.Environments.SerialReader) step() (control.reinforcement_learning.Environments.FakeEnv.FakeEnv method) (control.reinforcement_learning.Environments.PyBulletPendulumEnv.PyBulletPendulumEnv method) (control.reinforcement_learning.Environments.RealPendulumEnv.RealPendulumEnv method) store_tuple() (control.reinforcement_learning.DQN.ReplayBuffer.ReplayBuffer method)

T

total_energy() (control.pid.classes.EnergyController.EnergyController method) train() (control.reinforcement_learning.DQN.Agent.Agent method)

train_batch_gradientTape() (control.reinforcement_learning.DQN.DeepQNetwork.DeepQNetwork method) train_model() (control.reinforcement_learning.DQN.Agent.Agent method) train_on_batch() (control.reinforcement_learning.DQN.DeepQNetwork.DeepQNetwork method)