training_node.TrainingNode Class Reference

Inheritance diagram for training_node.TrainingNode:

Collaboration diagram for training_node.TrainingNode:

Public Member Functions
def	__init__ (self, policy, actions, laser_sample_count, max_episode_length, learn_rate)
def	on_crash (self, _)
def	get_episode_summary (self)
def	on_complete_episode (self)
def	on_receive_laser_scan (self, message)
def	on_complete_step (self, state, action, reward, next_state)
def	check_car_orientation (self)
def	on_model_state_callback (self, message)
Public Member Functions inherited from reinforcement_learning_node.ReinforcementLearningNode
def	__init__ (self, actions, laser_sample_count)
def	perform_action (self, action_index)
def	convert_laser_message_to_tensor (self, message, use_device=True)
def	on_receive_laser_scan (self, message)

Public Attributes
	policy
	max_episode_length
	episode_count
	episode_length
	total_step_count
	cumulative_reward
	is_terminal_step
	net_output_debug_string
	episode_length_history
	cumulative_reward_history
	state
	action
	car_position
	car_orientation
	drive_forward
	steps_with_wrong_orientation
	episode_start_time_real
	episode_start_time_sim
	optimizer
	episode_result_publisher
Public Attributes inherited from reinforcement_learning_node.ReinforcementLearningNode
	scan_indices
	laser_sample_count
	actions
	drive_parameters_publisher

Detailed Description

Abstract class for all methods that are common between
Q-Learning training and Policy Gradient training

Definition at line 21 of file training_node.py.

Constructor & Destructor Documentation

def training_node.TrainingNode.__init__	(		self,
			policy,
			actions,
			laser_sample_count,
			max_episode_length,
			learn_rate
	)

Definition at line 32 of file training_node.py.

Member Function Documentation

def training_node.TrainingNode.check_car_orientation

(

self

)

Definition at line 140 of file training_node.py.

Here is the caller graph for this function:

def training_node.TrainingNode.get_episode_summary

(

self

)

Definition at line 73 of file training_node.py.

Here is the caller graph for this function:

def training_node.TrainingNode.on_complete_episode

(

self

)

Definition at line 92 of file training_node.py.

Here is the call graph for this function:

Here is the caller graph for this function:

def training_node.TrainingNode.on_complete_step	(		self,
			state,
			action,
			reward,
			next_state
	)

Definition at line 137 of file training_node.py.

Here is the caller graph for this function:

def training_node.TrainingNode.on_crash	(		self,
			_
	)

Definition at line 69 of file training_node.py.

def training_node.TrainingNode.on_model_state_callback	(		self,
			message
	)

Definition at line 154 of file training_node.py.

def training_node.TrainingNode.on_receive_laser_scan	(		self,
			message
	)

Definition at line 111 of file training_node.py.

Here is the call graph for this function:

Member Data Documentation

training_node.TrainingNode.action

Definition at line 49 of file training_node.py.

training_node.TrainingNode.car_orientation

Definition at line 51 of file training_node.py.

training_node.TrainingNode.car_position

Definition at line 50 of file training_node.py.

training_node.TrainingNode.cumulative_reward

Definition at line 41 of file training_node.py.

training_node.TrainingNode.cumulative_reward_history

Definition at line 46 of file training_node.py.

training_node.TrainingNode.drive_forward

Definition at line 53 of file training_node.py.

training_node.TrainingNode.episode_count

Definition at line 38 of file training_node.py.

training_node.TrainingNode.episode_length

Definition at line 39 of file training_node.py.

training_node.TrainingNode.episode_length_history

Definition at line 45 of file training_node.py.

training_node.TrainingNode.episode_result_publisher

Definition at line 66 of file training_node.py.

training_node.TrainingNode.episode_start_time_real

Definition at line 56 of file training_node.py.

training_node.TrainingNode.episode_start_time_sim

Definition at line 57 of file training_node.py.

training_node.TrainingNode.is_terminal_step

Definition at line 42 of file training_node.py.

training_node.TrainingNode.max_episode_length

Definition at line 36 of file training_node.py.

training_node.TrainingNode.net_output_debug_string

Definition at line 44 of file training_node.py.

training_node.TrainingNode.optimizer

Definition at line 59 of file training_node.py.

training_node.TrainingNode.policy

Definition at line 35 of file training_node.py.

training_node.TrainingNode.state

Definition at line 48 of file training_node.py.

training_node.TrainingNode.steps_with_wrong_orientation

Definition at line 54 of file training_node.py.

training_node.TrainingNode.total_step_count

Definition at line 40 of file training_node.py.

---

The documentation for this class was generated from the following file:

• /home/travis/build/Autonomous-Racing-PG/ar-tu-do/docs/master/ros_ws/src/autonomous/reinforcement_learning/scripts/training_node.py