Pseudo code for sarsa lambda

sarsa_lambda.pseudocode

Procedure SARSA(lambda)
Initialize Q(s,a) arbitrarily and e(s,a)=0 for all s,a pairs
Repeat(per episode):
	Initialize s,a
	e(s,a)=0
    Repeat(per timestep in each episode):
        Take action a, observe r,s`
        Choose a` from s` via epsilon-greedy policy Q
        error = r+discount*Q(s`,a`)-Q(s,a)
        any e(s,:)=0
        e(s,a)=1
        Q = Q + learn_rate*error*e
        e = e*discount*lambda