15 lines
376 B
Python
15 lines
376 B
Python
from majiang_rl import MahjongEnv
|
|
from majiang_rl.rl import RandomAgent, run_training
|
|
|
|
|
|
def main():
|
|
env = MahjongEnv()
|
|
agent = RandomAgent()
|
|
results = run_training(env, agent, episodes=5)
|
|
for idx, result in enumerate(results, start=1):
|
|
print(f"Episode {idx}: reward={result.total_reward}, steps={result.steps}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|