www2171668 / pycharm Goto Github PK

(alfn) huang@huang:~/Project/ALF2022/alf/examples$ python -m alf.bin.train --gin_file=sac_fetchreach.gin --root_dir=/tmp/sac_fetchreach_2 WARNING:root:Argument whitelist is deprecated. Please use allowlist. WARNING:root:Argument whitelist is deprecated. Please use allowlist. WARNING:root:Argument whitelist is deprecated. Please use allowlist. WARNING:root:Argument whitelist is deprecated. Please use allowlist. WARNING:root:Argument blacklist is deprecated. Please use denylist. I0329 14:08:15.470984 140332633777984 parallel_environment.py:94] Spawning all processes. I0329 14:08:15.608962 140332633777984 parallel_environment.py:101] All processes started. I0329 14:08:17.435215 140332633777984 policy_trainer.py:333] observation_spec=BoundedTensorSpec(shape=(13,), dtype=torch.float32, minimum=array(-inf, dtype=float32), maximum=array(inf, dtype=float32)) I0329 14:08:17.435640 140332633777984 policy_trainer.py:334] action_spec=BoundedTensorSpec(shape=(4,), dtype=torch.float32, minimum=array(-1., dtype=float32), maximum=array(1., dtype=float32)) I0329 14:08:17.436043 140332633777984 policy_trainer.py:349] transformed_observation_spec=BoundedTensorSpec(shape=(13,), dtype=torch.float32, minimum=array(-inf, dtype=float32), maximum=array(inf, dtype=float32)) /home/huang/Project/ALF2022/alf/networks/projection_networks.py:211: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /opt/conda/conda-bld/pytorch_1616554786529/work/torch/csrc/utils/tensor_numpy.cpp:143.) action_high = torch.as_tensor(action_spec.maximum) I0329 14:08:17.628263 140332633777984 sac_algorithm.py:83] Target entropy is calculated for SacAlgorithm: -3.6651629198780027. /home/huang/Project/ALF2022/alf/utils/checkpoint_utils.py:187: UserWarning: There is no checkpoint in directory /tmp/sac_fetchreach_2/train/algorithm. Train from scratch "Train from scratch" % self._ckpt_dir) I0329 14:08:17.776358 140332633777984 policy_trainer.py:155] Use kill -12 9037to request checkpoint during training. I0329 14:08:17.776484 140332633777984 policy_trainer.py:161] Usekill -10 9037 to request debugging. I0329 14:08:18.021416 140332633777984 policy_trainer.py:449] sac_fetchreach.gin -> sac_fetchreach_2: 0 time=0.242 throughput=0.00 I0329 14:08:19.177697 140332633777984 policy_trainer.py:449] sac_fetchreach.gin -> sac_fetchreach_2: 5 time=0.225 throughput=0.00 I0329 14:08:20.380865 140332633777984 policy_trainer.py:449] sac_fetchreach.gin -> sac_fetchreach_2: 10 time=0.259 throughput=0.00 I0329 14:08:21.538066 140332633777984 policy_trainer.py:449] sac_fetchreach.gin -> sac_fetchreach_2: 15 time=0.233 throughput=0.00 ^CDo you want to save checkpoint? (y/n): n I0329 14:08:25.133682 140332633777984 parallel_environment.py:168] Closing all processes. I0329 14:08:25.134826 140332633777984 parallel_environment.py:171] All processes closed.