python run_baseline_parallel_fast.py

[sunflower330]

Why does this code stop with an error when the ep_1ength reaches the set 20480？

step: 20479 event: 4.00 level: 8.00 heal: 3.66 op_lvl: 0.00 dead: -0.40 badge: 0.00 explore: 29.76 sum: 45.02Process ForkServerProcess-1:
Traceback (most recent call last):
File "/home/qing/anaconda3/envs/pokey/lib/python3.10/multiprocessing/process.py", line 315, in _bootstrap
self.run()
File "/home/qing/anaconda3/envs/pokey/lib/python3.10/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/home/qing/anaconda3/envs/pokey/lib/python3.10/site-packages/stable_baselines3/common/vec_env/subproc_vec_env.py", line 59, in _worker
remote.send(getattr(env, data))
AttributeError: 'RedGymEnv' object has no attribute 'explore_map'
Traceback (most recent call last):
File "/home/qing/PokemonRedExperiments/baselines/run_baseline_parallel_fast.py", line 82, in
model.learn(total_timesteps=(ep_length)num_cpu10, callback=CallbackList(callbacks))
File "/home/qing/anaconda3/envs/pokey/lib/python3.10/site-packages/stable_baselines3/ppo/ppo.py", line 308, in learn
return super().learn(
File "/home/qing/anaconda3/envs/pokey/lib/python3.10/site-packages/stable_baselines3/common/on_policy_algorithm.py", line 259, in learn
continue_training = self.collect_rollouts(self.env, callback, self.rollout_buffer, n_rollout_steps=self.n_steps)
File "/home/qing/anaconda3/envs/pokey/lib/python3.10/site-packages/stable_baselines3/common/on_policy_algorithm.py", line 184, in collect_rollouts
if callback.on_step() is False:
File "/home/qing/anaconda3/envs/pokey/lib/python3.10/site-packages/stable_baselines3/common/callbacks.py", line 104, in on_step
return self._on_step()
File "/home/qing/anaconda3/envs/pokey/lib/python3.10/site-packages/stable_baselines3/common/callbacks.py", line 208, in _on_step
continue_training = callback.on_step() and continue_training
File "/home/qing/anaconda3/envs/pokey/lib/python3.10/site-packages/stable_baselines3/common/callbacks.py", line 104, in on_step
return self._on_step()
File "/home/qing/PokemonRedExperiments/baselines/tensorboard_callback.py", line 58, in _on_step
explore_map = np.array(self.training_env.get_attr("explore_map"))
File "/home/qing/anaconda3/envs/pokey/lib/python3.10/site-packages/stable_baselines3/common/vec_env/base_vec_env.py", line 367, in get_attr
return self.venv.get_attr(attr_name, indices)
File "/home/qing/anaconda3/envs/pokey/lib/python3.10/site-packages/stable_baselines3/common/vec_env/subproc_vec_env.py", line 173, in get_attr
return [remote.recv() for remote in target_remotes]
File "/home/qing/anaconda3/envs/pokey/lib/python3.10/site-packages/stable_baselines3/common/vec_env/subproc_vec_env.py", line 173, in
return [remote.recv() for remote in target_remotes]
File "/home/qing/anaconda3/envs/pokey/lib/python3.10/multiprocessing/connection.py", line 255, in recv
buf = self._recv_bytes()
File "/home/qing/anaconda3/envs/pokey/lib/python3.10/multiprocessing/connection.py", line 419, in _recv_bytes
buf = self._recv(4)
File "/home/qing/anaconda3/envs/pokey/lib/python3.10/multiprocessing/connection.py", line 388, in _recv
raise EOFError
EOFError

[PWhiddy]

Hey!

I see:

AttributeError: 'RedGymEnv' object has no attribute 'explore_map'

have you made any modifications to the code?