FINAL_EPSILON = 0.0001 ,maybe INITIAL_EPSILON = 1?
MemoryCrash opened this issue · comments
FINAL_EPSILON = 0.0001
INITIAL_EPSILON = 0.0001
epsilon = INITIAL_EPSILON
"so in this condition "epsilon" will never be update."
if epsilon > FINAL_EPSILON and t > OBSERVE:
epsilon -= (INITIAL_EPSILON - FINAL_EPSILON) / EXPLORE