from azul_marl_env import azul_v1_2players, azul_v1_3players, azul_v1_4players

env_2players = azul_v1_2players()
env_3players = azul_v1_3players()
env_4players = azul_v1_4players()

env_2players_custom_max_moves = azul_v1_2players(max_moves=100)

from azul_marl_env import AzulEnv

env = AzulEnv(player_count=2)
env = AzulEnv(player_count=3)
env = AzulEnv(player_count=4) 

env = AzulEnv(player_count=2, max_moves=100)

from azul_marl_env import azul_v1_2players
import random

# Create and reset the environment
env = azul_v1_2players()
observation, info = env.reset()

# Iterate through agents
for agent in env.agent_iter():
    # Get current agent's observation and info
    observation, reward, termination, truncation, info = env.last()
    
    if termination or truncation:
        break
        
    # Get valid moves for current agent
    valid_moves = info["valid_moves"]
    # Select a random valid move
    action = random.choice(valid_moves)
    # Execute the move
    env.step(action)
    
    # Render the environment (optional)
    env.render()

# Close the environment
env.close()

from azul_marl_env import azul_v1_2players
import random

def play_random_game():
    env = azul_v1_2players()
    observation, info = env.reset()
    
    for agent in env.agent_iter():
        observation, reward, termination, truncation, info = env.last()
        
        if termination or truncation:
            print(f"Game finished! Final scores: {[player['score'] for player in observation['players']]}")
            break
            
        # Get valid moves and make a random move
        valid_moves = info["valid_moves"]
        if valid_moves:
            action = random.choice(valid_moves)
            env.step(action)
    
    env.close()

play_random_game()