def __init__(self):
super(DouDiZhuPokerEnv, self).__init__()
self.public_state = DouDiZhuPokerPublicState()
self.private_state = DouDiZhuPokerPrivateState()
self.person_states = [
DouDiZhuPokerPersonState() for i in range(3 + 1)
] ## Three players and one chance player
def __available_actions_generate_all__(cls):
public_state = DouDiZhuPokerPublicState()
person_state = DouDiZhuPokerPersonState()
public_state.__is_response__ = False
person_state.__hand_cards__ = DouDiZhuPokerHandCards("")
for i in range(13):
for j in range(4):
person_state.hand_cards.add_cards(
DouDiZhuActionElement.rank_to_str[i])
person_state.hand_cards.add_cards(DouDiZhuActionElement.rank_to_str[
DouDiZhuActionElement.str_to_rank["r"]])
person_state.hand_cards.add_cards(DouDiZhuActionElement.rank_to_str[
DouDiZhuActionElement.str_to_rank["R"]])
actions = dict()
patterns = []
if public_state.phase == 0:
patterns.append(AllPatterns["i_cheat"])
patterns.append(AllPatterns["i_bid"])
else:
if public_state.is_response == False:
for p in AllPatterns:
if p != "i_cheat" and p != "i_invalid":
patterns.append(AllPatterns[p])
else:
patterns.append(public_state.license_action.pattern)
if public_state.license_action.pattern[6] == 1:
patterns.append(AllPatterns["p_4_1_0_0_0"]) # rank = 10
patterns.append(AllPatterns["x_rocket"]) # rank = 100
if public_state.license_action.pattern[6] == 10:
patterns.append(AllPatterns["x_rocket"]) # rank = 100
patterns.append(AllPatterns["i_cheat"])
actions = dict()
for pattern in patterns:
numMaster = pattern[1]
numMasterPoint = pattern[2]
isStraight = pattern[3]
numSlave = pattern[4]
MasterCount = -1
SlaveCount = -1
if numMaster > 0:
MasterCount = int(numMaster / numMasterPoint)
if "i_invalid" == pattern[0]:
continue
if "i_cheat" == pattern[0]:
action_key = DouDiZhuPokerAction.__master_slave_cards_to_key__(
[DouDiZhuActionElement.str_to_rank["x"]], [])
action = DouDiZhuPokerAction(
[DouDiZhuActionElement.str_to_rank["x"]], [])
if action_key in actions:
if cls.__action_priority__(action,
actions[action_key]) > 0:
actions[action_key] = action
else:
actions[action_key] = action
continue
if "i_bid" == pattern[0]:
action_key = DouDiZhuPokerAction.__master_slave_cards_to_key__(
[DouDiZhuActionElement.str_to_rank["b"]], [])
action = DouDiZhuPokerAction(
[DouDiZhuActionElement.str_to_rank["b"]], [])
if action_key in actions:
if cls.__action_priority__(action,
actions[action_key]) > 0:
actions[action_key] = action
else:
actions[action_key] = action
continue
if pattern[0] == "x_rocket":
if person_state.hand_cards.card_pointrank_count[DouDiZhuActionElement.str_to_rank["r"]] == 1 and \
person_state.hand_cards.card_pointrank_count[DouDiZhuActionElement.str_to_rank["R"]] == 1:
action_key = DouDiZhuPokerAction.__master_slave_cards_to_key__(
[
DouDiZhuActionElement.str_to_rank["r"],
DouDiZhuActionElement.str_to_rank["R"]
], [])
action = DouDiZhuPokerAction([
DouDiZhuActionElement.str_to_rank["r"],
DouDiZhuActionElement.str_to_rank["R"]
], [])
if action_key in actions:
if cls.__action_priority__(action,
actions[action_key]) > 0:
actions[action_key] = action
else:
actions[action_key] = action
continue
if pattern[1] + pattern[4] > person_state.hand_cards.num_cards:
continue
sum1 = 0
for count in range(MasterCount, 5, 1):
sum1 += person_state.hand_cards.count2num[count]
if sum1 < numMasterPoint:
continue
### action with cards
mCardss = []
mCardss = DouDiZhuPokerEnv.__extractMasterCards__(
person_state.hand_cards, pattern)
for mCards in mCardss:
if numSlave == 0:
action_key = DouDiZhuPokerAction.__master_slave_cards_to_key__(
mCards, [])
action = DouDiZhuPokerAction(mCards, [])
if action_key in actions:
if cls.__action_priority__(action,
actions[action_key]) > 0:
actions[action_key] = action
else:
actions[action_key] = action
continue
sCardss = DouDiZhuPokerEnv.__extractSlaveCards__(
person_state.hand_cards, mCards, pattern)
for sCards in sCardss:
action_key = DouDiZhuPokerAction.__master_slave_cards_to_key__(
mCards, sCards)
action = DouDiZhuPokerAction(mCards, sCards)
if action_key in actions:
if cls.__action_priority__(action,
actions[action_key]) > 0:
actions[action_key] = action
else:
actions[action_key] = action
return actions
def init(self, params=dict()):
'''
Initialize the DouDiZhuPoker game environment with the initialization params.\n
The initialization is a dict with some options\n
1. param_backward_enable: whether to record all history states. if you need call the backward function, please set it to True. default False\n
2. param_start_turn: players[start_turn] is first normal player to take an action\n
An example of the initialization param is {"param_start_turn":2,"param_backward_enable":True}\n
:param params: the initialization params
:return: infos, public_state, person_states, private_state
'''
self.public_state = DouDiZhuPokerPublicState()
self.private_state = DouDiZhuPokerPrivateState()
self.person_states = [
DouDiZhuPokerPersonState() for i in range(3 + 1)
] ## Three players and one chance player
logger = roomai.get_logger()
if "param_backward_enable" in params:
self.public_state.__param_backward_enable__ = params[
"param_backward_enable"]
else:
self.public_state.__param_backward_enable__ = False
logger.info("param_backward_enable = " +
str(self.public_state.param_backward_enable))
if "param_start_turn" in params:
self.public_state.__param_start_turn__ = params["param_start_turn"]
else:
self.public_state.__param_start_turn__ = int(random.random() * 3)
logger.info("param_start_turn = %d" %
(self.public_state.param_start_turn))
if "param_num_normal_players" in params:
logger.warning(
"DouDiZhu is a game of 3 normal players (1 chance player). Ingores the \"num_normal_players\" option"
)
self.public_state.__param_num_normal_players__ = 3
logger.info("param_num_normal_players = 3")
self.public_state.__turn__ = 3
self.public_state.__phase__ = 0
self.public_state.__epoch__ = 0
self.public_state.__landlord_id = -1
self.public_state.__license_playerid__ = self.public_state.turn
self.public_state.__license_action__ = None
self.public_state.__is_terminal__ = False
self.public_state.__scores__ = [0, 0, 0]
self.private_state.__unused_cards__ = DouDiZhuPokerHandCards("")
for i in range(13):
for j in range(4):
self.private_state.__unused_cards__.add_cards(
DouDiZhuActionElement.rank_to_str[i])
self.private_state.__unused_cards__.add_cards(
DouDiZhuActionElement.rank_to_str[13])
self.private_state.__unused_cards__.add_cards(
DouDiZhuActionElement.rank_to_str[14])
for i in range(3):
self.person_states[i].__hand_cards__ = DouDiZhuPokerHandCards("")
self.person_states[i].__id__ = i
self.person_states[i].__id__ = 3
self.person_states[3].__available_actions__ = dict()
for card in self.private_state.__unused_cards__.key:
self.person_states[3].__available_actions__[
card] = DouDiZhuPokerActionChance.lookup(card)
infos = self.__gen_infos__()
self.__gen_state_history_list__()
return infos, self.public_state, self.person_states, self.private_state