parameters_policy_gradient Namespace Reference

Classes
class	Policy

Variables
list	ACTIONS
	ACTION_COUNT = len(ACTIONS)
int	LASER_SAMPLE_COUNT = 8
	MODEL_FILENAME
bool	CONTINUE = False
float	DISCOUNT_FACTOR = 0.99
int	MAX_EPISODE_LENGTH = 5000
float	LEARNING_RATE = 0.001

Variable Documentation

parameters_policy_gradient.ACTION_COUNT = len(ACTIONS)

Definition at line 11 of file parameters_policy_gradient.py.

list parameters_policy_gradient.ACTIONS

Initial value:

= [(-0.8, 0.1), (0.8, 0.1), (0.5, 0.2),
           (-0.5, 0.2), (0, 0.2), (0, 0.4)]

Definition at line 9 of file parameters_policy_gradient.py.

bool parameters_policy_gradient.CONTINUE = False

Definition at line 23 of file parameters_policy_gradient.py.

float parameters_policy_gradient.DISCOUNT_FACTOR = 0.99

Definition at line 25 of file parameters_policy_gradient.py.

int parameters_policy_gradient.LASER_SAMPLE_COUNT = 8

Definition at line 16 of file parameters_policy_gradient.py.

float parameters_policy_gradient.LEARNING_RATE = 0.001

Definition at line 29 of file parameters_policy_gradient.py.

int parameters_policy_gradient.MAX_EPISODE_LENGTH = 5000

Definition at line 27 of file parameters_policy_gradient.py.

parameters_policy_gradient.MODEL_FILENAME

Initial value:

= os.path.join(RosPack().get_path(
    "reinforcement_learning"), "policy_gradient.to")

Definition at line 18 of file parameters_policy_gradient.py.