Hi,
In my local, I test the agent.py and it can construct the agent specs successfully. However, in the online system, it reports an error on it.
WARNING: Your kernel does not support swap limit capabilities or the cgroup is not mounted. Memory limited without swap.
X.Org X Server 1.19.6
Release Date: 2017-12-20
X Protocol Version 11, Revision 0
Build Operating System: Linux 4.4.0-168-generic x86_64 Ubuntu
Current Operating System: Linux dbe6a3258af2 4.15.0-91-generic #92-Ubuntu SMP Fri Feb 28 11:09:48 UTC 2020 x86_64
Kernel command line: BOOT_IMAGE=/boot/vmlinuz-4.15.0-91-generic root=UUID=ebf7b11c-e1bc-4725-a0d2-d42aee76509f ro net.ifnames=0 consoleblank=600 console=tty0 console=ttyS0,115200n8 nospectre_v2 nopti noibrs noibpb
Build Date: 14 November 2019 06:20:00PM
xorg-server 2:1.19.6-1ubuntu4.4 (For technical support please see http://www.ubuntu.com/support)
Current version of pixman: 0.34.0
Before reporting problems, check http://wiki.x.org
to make sure that you have the latest version.
Markers: (--) probed, (**) from config file, (==) default setting,
(++) from command line, (!!) notice, (II) informational,
(WW) warning, (EE) error, (NI) not implemented, (??) unknown.
(++) Log file: "./xdummy.log", Time: Sun Aug 23 13:39:43 2020
(++) Using config file: "/etc/X11/xorg.conf"
(==) Using system config directory "/usr/share/X11/xorg.conf.d"
INFO:/tmp/codalab/tmp7DqBBD/run/program/evaluate.py:root_path=[metadata, evaluate.py, envision, smarts, cli, .DS_Store]
INFO:/tmp/codalab/tmp7DqBBD/run/program/evaluate.py:input_dir=[history, ref, metadata, tmpQigq9U.txt, tmpzWXzGu.zip, tmpHMDOVA.zip, coopetition, tmp4vQwzL.zip, scores, tmpzIoZzW.txt, res]
INFO:/tmp/codalab/tmp7DqBBD/run/program/evaluate.py:output_dir=[metadata]
INFO:/tmp/codalab/tmp7DqBBD/run/program/evaluate.py:submission_dir=[agent.py, metadata, checkpoint, __pycache__, rllib_agent_config.py, networks.py, utils]
INFO:/tmp/codalab/tmp7DqBBD/run/program/evaluate.py:eval_scenarios_dir=[crossroads, roundabout, double_merge, ramp, t_junction]
INFO:/tmp/codalab/tmp7DqBBD/run/program/evaluate.py:scores_dir=[metadata]
INFO:/tmp/codalab/tmp7DqBBD/run/program/evaluate.py:submission_dir=/tmp/codalab/tmp7DqBBD/run/input/res, eval_scenarios_dir=/tmp/codalab/tmp7DqBBD/run/input/ref/dataset_evaluation, scores_dir=/tmp/codalab/tmp7DqBBD/run/output
2020-08-23 13:39:46,878 INFO catalog.py:308 -- Wrapping as
2020-08-23 13:39:47,062 INFO catalog.py:308 -- Wrapping as
2020-08-23 13:39:48,483 INFO catalog.py:308 -- Wrapping as
2020-08-23 13:39:49,094 INFO catalog.py:308 -- Wrapping as
Traceback (most recent call last):
File "/tmp/codalab/tmp7DqBBD/run/program/evaluate.py", line 319, in
agent_specs = load_agent_submission(submission_dir)
File "/tmp/codalab/tmp7DqBBD/run/program/evaluate.py", line 84, in load_agent_submission
import agent as agent_submission
File "/tmp/codalab/tmp7DqBBD/run/input/res/agent.py", line 155, in
config.spec["act"],
File "/tmp/codalab/tmp7DqBBD/run/input/res/agent.py", line 130, in __init__
self._policy_mapping[name].set_weights(weights)
File "/tmp/codalab/tmp7DqBBD/run/input/res/agent.py", line 46, in set_weights
self._policy.set_weights(weights)
File "/usr/local/lib/python3.7/dist-packages/ray/rllib/policy/tf_policy.py", line 374, in set_weights
return self._variables.set_weights(weights)
File "/usr/local/lib/python3.7/dist-packages/ray/experimental/tf_utils.py", line 182, in set_weights
assert assign_list, ("No variables in the input matched those in the "
AssertionError: No variables in the input matched those in the network. Possible cause: Two networks were defined in the same TensorFlow graph. To fix this, place each network definition in its own tf.Graph.
ok, we are going to download your submission to track this error.
Posted by: DAI2020 @ Aug. 26, 2020, 2:42 a.m.