nolimit_holdem_human.py

''' A toy example of playing against pretrianed AI on Leduc Hold'em
'''
from rlcard.agents import RandomAgent

import rlcard
from rlcard import models
from rlcard.agents import NolimitholdemHumanAgent as HumanAgent
from rlcard.utils import print_card

# Make environment
# Set 'record_action' to True because we need it to print results
env = rlcard.make('no-limit-holdem', config={'record_action': True})

human_agent = HumanAgent(env.action_num)
human_agent2 = HumanAgent(env.action_num)
# random_agent = RandomAgent(action_num=env.action_num)

env.set_agents([human_agent, human_agent2])


while (True):
    print(">> Start a new game")

    trajectories, payoffs = env.run(is_training=False)
    # If the human does not take the final action, we need to
    # print other players action
    final_state = trajectories[0][-1][-2]
    action_record = final_state['action_record']
    state = final_state['raw_obs']
    _action_list = []
    for i in range(1, len(action_record)+1):
        if action_record[-i][0] == state['current_player']:
            break
        _action_list.insert(0, action_record[-i])
    for pair in _action_list:
        print('>> Player', pair[0], 'chooses', pair[1])

    # Let's take a look at what the agent card is
    print('===============     Cards all Players    ===============')
    for hands in env.get_perfect_information()['hand_cards']:
        print_card(hands)

    print('===============     Result     ===============')
    if payoffs[0] > 0:
        print('You win {} chips!'.format(payoffs[0]))
    elif payoffs[0] == 0:
        print('It is a tie.')
    else:
        print('You lose {} chips!'.format(-payoffs[0]))
    print('')

    input("Press any key to continue...")