qtable Namespace Reference

Functions
def	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()

def qtable.rendertrial

(

maxiter = 100

)

Roll-out from random state using greedy policy.

Definition at line 31 of file qtable.py.

Variable Documentation

u

u

Initial value:

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

Definition at line 52 of file qtable.py.