try more time steps

This commit is contained in:
Arthur Lu 2024-03-14 10:57:18 -07:00
parent 848ea719b7
commit dd5889da33

View File

@ -25,8 +25,6 @@ def test(model, env, test_num=1000):
action, _states = model.predict(obs)
obs, rewards, done, info = env.step(action)
print(action, obs, rewards)
return total_correct / test_num
if __name__ == "__main__":
@ -36,5 +34,5 @@ if __name__ == "__main__":
print(env)
print(model)
train(model, env, total_timesteps=10000)
print(test(model, env, test_num=1))
train(model, env, total_timesteps=500000)
print(test(model, env))