luisgarciar / 3d-bin-packing Goto Github PK

Hello, can you tell me whether the 3D boxing test of the PPO environment is successful? Here I display: ValueError: operators could not be broadcast together with shapes (10,) (3,) (10,). How can I handle this error?

Hello,

I cannot find the demo file "demo_ffd" mentioned in README.md:

-->A demo notebook demo_ffd implementing the heuristic-based method 'First Fit Decreasing' is available in the nb
folder.

Hi,

I had an error using the example notebooks on my PC.
The error is the same one mentioned here:
https://stackoverflow.com/questions/76233793/getting-environment-must-inherit-from-the-gym-env-when-it-already-does-in-stable

Their solution worked for me too.
I added the following line to the requirements file to fix the error:
stable-baselines3==1.7

Best,

Hi Luis,

I am trying to run the code, even if it is difficult, I managed to bring all libraries to the same versions in requirements, but I get the following problem.

Can you help me?

model = MaskablePPO("MultiInputPolicy", env, verbose=2)
print("begin training")
model.learn(total_timesteps=1000)
print("done training")
model.save("ppo_mask")

Using cpu device
Wrapping the env with a Monitor wrapper
Wrapping the env in a DummyVecEnv.
begin training

TypeError Traceback (most recent call last)

in <cell line: 3>()
1 model = MaskablePPO("MultiInputPolicy", env, verbose=2)
2 print("begin training")
----> 3 model.learn(total_timesteps=1000)
4 print("done training")
5 model.save("ppo_mask")

3 frames

/usr/local/lib/python3.10/dist-packages/sb3_contrib/ppo_mask/ppo_mask.py in learn(self, total_timesteps, callback, log_interval, tb_log_name, reset_num_timesteps, use_masking, progress_bar)
512 iteration = 0
513
--> 514 total_timesteps, callback = self._setup_learn(
515 total_timesteps,
516 callback,

/usr/local/lib/python3.10/dist-packages/sb3_contrib/ppo_mask/ppo_mask.py in _setup_learn(self, total_timesteps, callback, reset_num_timesteps, tb_log_name, use_masking, progress_bar)
237 # Avoid resetting the environment when calling .learn() consecutive times
238 if reset_num_timesteps or self._last_obs is None:
--> 239 self._last_obs = self.env.reset()
240 self._last_episode_starts = np.ones((self.env.num_envs,), dtype=bool)
241 # Retrieve unnormalized observation for saving into the buffer

/usr/local/lib/python3.10/dist-packages/stable_baselines3/common/vec_env/dummy_vec_env.py in reset(self)
76 maybe_options = {"options": self._options[env_idx]} if self._options[env_idx] else {}
77 obs, self.reset_infos[env_idx] = self.envs[env_idx].reset(seed=self._seeds[env_idx], **maybe_options)
---> 78 self._save_obs(env_idx, obs)
79 # Seeds and options are only used once
80 self._reset_seeds()

/usr/local/lib/python3.10/dist-packages/stable_baselines3/common/vec_env/dummy_vec_env.py in _save_obs(self, env_idx, obs)
108 self.buf_obs[key][env_idx] = obs
109 else:
--> 110 self.buf_obs[key][env_idx] = obs[key] # type: ignore[call-overload]
111
112 def _obs_from_buf(self) -> VecEnvObs:

TypeError: string indices must be integers