default=0.99,
type=float,
help="discount_factor. Default = 0.99",
dest="discount_factor")
args = parser.parse_args()
#DP(args,8)
States = environment.CreateStates(args.LT_f, args.LT_s, args.Inv_Max,
args.Inv_Min, args.OrderFast,
args.OrderSlow)
Actions = environment.CreateActions(args.OrderFast, args.OrderSlow)
dict_states = environment.CreateDictStates(States)
with open('./A3C_policy.csv') as f:
#States = []
policy = []
for line in f:
#States.append(line.split(sep=';')[:2])
policy.append(line.split(sep=';')[0:82])
#a_prob_s.append(line.split(sep=';')[10:16])
for index, i in enumerate(policy):
policy[index] = [float(j) for j in policy[index]]
#print(policy)
P = PI.TransitionProbs(States, Actions, args.Demand_Max, args.LT_s,
args.LT_f, args.h, args.b, args.C_s, args.C_f,
args.Inv_Max, args.Inv_Min, args.cap_fast,
args.cap_slow, dict_states)
print('Cost: ', MarkovChain.TestPolicy(States, P, policy))
