def reset(self): # North and South
"""
:param reshuffle: whether reshuffle the hands for the predeal seats
:return: deal
"""
if len(self.scores_dicts) == 0:
raise Exception("Please set the data in adavance")
self.bidding_history = np.zeros(36, dtype=np.uint8) # 1C 1D 1H 1S 1N ... 7N (PASS - not considered)
self.max_bid = -1
self.n_pass = 0
self.turn = self.bidding_seats[0] # the first one.
self.done = False
self.strain_declarer = {0: {}, 1: {}}
self.group_declarer = -1
idx = self.loading_data_order[self.loading_count]
predeal, self.rewards_table = self.pre_deals_dicts[idx], self.scores_dicts[idx]
self.loading_count += 1
self.one_hot_deal = np.zeros((len(Seat), len(FULL_DECK)), dtype=np.uint8)
for seat, hands in predeal.items():
self.one_hot_deal[seat] = one_hot_holding(hands) # one hot cards
# update the deal
self.deal = Deal.prepare(predeal)
if self.loading_count >= len(self.loading_data_order): # reshuffle the indices
self.loading_count = 0
self.loading_data_order = random.sample(list(np.arange(len(self.pre_deals_dicts))),
len(self.pre_deals_dicts))
self.traverse_flag = True
if self.debug:
convert_hands2string(self.deal)
# if not allocated, zero vector is returned.
return (self.one_hot_deal[self.turn], self.bidding_history), {"turn": Seat[self.turn], "max_bid": self.max_bid,
"traverse": self.traverse_flag}
def evaluate_new_sample(self,
predeal_seats=None,
declarer=None): # North and South
"""
:param predeal_seats: if not None, allocate cards to those seats. e.g. [0, 1] stands for North and East
:param reshuffle: whether reshuffle the hands for the predeal seats
:return: deal
"""
if predeal_seats is None:
predeal_seats = self.bidding_seats
predeal = {}
random.shuffle(self.cards)
i = 0
self.one_hot_deal = np.zeros((len(Seat), len(FULL_DECK)),
dtype=np.uint8)
for seat in sorted(predeal_seats):
predeal[seat] = self.cards[i:i + len(Rank)]
self.one_hot_deal[seat] = one_hot_holding(
predeal[seat]) # one hot cards
i += len(Rank) # shift the index
self.deal = Deal.prepare(predeal)
if self.debug:
convert_hands2string(self.deal)
rewards_dict = {}
if declarer is not None:
rewards = self.score_fn(dealer=self.deal,
declarer=declarer,
tries=self.nmc,
mode=self.score_mode)
rewards_dict[declarer] = rewards
else:
for s in self.bidding_seats:
rewards = self.score_fn(dealer=self.deal,
declarer=s,
tries=self.nmc,
mode=self.score_mode)
rewards_dict[s] = rewards
return predeal, rewards_dict, self.one_hot_deal[self.bidding_seats]
def reset(self, predeal_seats=None, reshuffle=True): # North and South
"""
:param predeal_seats: if not None, allocate cards to those seats. e.g. [0, 1] stands for North and East
:param reshuffle: whether reshuffle the hands for the predeal seats
:return: deal
"""
self.bidding_history = np.zeros(
36,
dtype=np.uint8) # 1C 1D 1H 1S 1N ... 7N (PASS - not considered)
self.max_bid = -1
self.n_pass = 0
self.turn = self.bidding_seats[0] # the first one.
self.done = False
self.strain_declarer = {0: {}, 1: {}}
self.group_declarer = -1
if predeal_seats is None:
predeal_seats = self.bidding_seats
predeal = {}
random.shuffle(self.cards)
if reshuffle: # generate new hands for predeal seats.
i = 0
self.one_hot_deal = np.zeros((len(Seat), len(FULL_DECK)),
dtype=np.uint8)
for seat in sorted(predeal_seats):
predeal[seat] = self.cards[i:i + len(Rank)]
self.one_hot_deal[seat] = one_hot_holding(
predeal[seat]) # one hot cards
i += len(Rank) # shift the index
self.deal = Deal.prepare(predeal)
if self.debug:
convert_hands2string(self.deal)
# if not allocated, zero vector is returned.
return (self.one_hot_deal[self.turn], self.bidding_history), {
"turn": Seat[self.turn],
"max_bid": self.max_bid
}
from deal import Deal
import time
start = time.time()
# Strain 0: "C", 1: "D", 2: "H", 3: "S", 4: "N"
# Suit 0: "S", 1: "H", 2: "D", 3: "C"
predeal = {0: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]}
deal1 = Deal.prepare(predeal)
Deal.score(dealer=deal1, level=5, strain=0, declarer=3, tries=100)
print("%.2f seconds elapsed" % (time.time()-start))
