Functions
	rendertrial (maxiter=100)

Variables
float	DECAY_RATE = 0.99

	env = DPendulum()

list	h_rwd = []

float	LEARNING_RATE = 0.85

int	NEPISODES = 500

int	NSTEPS = 50

	NU = env.nu

	NX = env.nx

	Q = np.zeros([env.nx, env.nu])

float	Qref = reward + DECAY_RATE * np.max(Q[x2, :])

	RANDOM_SEED = int((time.time() % 10) * 1000)

	reward

float	rsum = 0.0

	u

	x = env.reset()

	x2

Detailed Description

Example of Q-table learning with a simple discretized 1-pendulum environment.

Function Documentation

◆ rendertrial()

rendertrial ( maxiter = 100 )

Roll-out from random state using greedy policy.

Definition at line 31 of file qtable.py.

Variable Documentation

◆ DECAY_RATE

float DECAY_RATE = 0.99

Definition at line 21 of file qtable.py.

◆ env

env = DPendulum()

Definition at line 24 of file qtable.py.

◆ h_rwd

list h_rwd = []

Definition at line 46 of file qtable.py.

◆ LEARNING_RATE

float LEARNING_RATE = 0.85

Definition at line 20 of file qtable.py.

◆ NEPISODES

int NEPISODES = 500

Definition at line 18 of file qtable.py.

◆ NSTEPS

int NSTEPS = 50

Definition at line 19 of file qtable.py.

◆ NU

NU = env.nu

Definition at line 26 of file qtable.py.

◆ NX

NX = env.nx

Definition at line 25 of file qtable.py.

◆ Q

Q = np.zeros([env.nx, env.nu])

Definition at line 28 of file qtable.py.

◆ Qref

float Qref = reward + DECAY_RATE * np.max(Q[x2, :])

Definition at line 58 of file qtable.py.

◆ RANDOM_SEED

RANDOM_SEED = int((time.time() % 10) * 1000)

Definition at line 13 of file qtable.py.

◆ reward

reward

Definition at line 55 of file qtable.py.

◆ rsum

float rsum = 0.0

Definition at line 50 of file qtable.py.

◆ u

u

Initial value:

=  np.argmax(
            Q[x, :] + np.random.randn(1, NU) / episode
        )

Definition at line 52 of file qtable.py.

◆ x

x = env.reset()

Definition at line 49 of file qtable.py.

◆ x2

x2