openai / multi-agent-emergence-environments Goto Github PK
View Code? Open in Web Editor NEWEnvironment generation code for the paper "Emergent Tool Use From Multi-Agent Autocurricula"
License: MIT License
Environment generation code for the paper "Emergent Tool Use From Multi-Agent Autocurricula"
License: MIT License
bin/examine.py examples/hide_and_seek_quadrant.jsonnet examples/lock_and_return.npz
Inferred:
names: examples/hide_and_seek_quadrant.jsonnet examples/lock_and_return.npz
arguments: {}
/home/amitmandliya/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/amitmandliya/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/amitmandliya/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/amitmandliya/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/amitmandliya/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/amitmandliya/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
/home/amitmandliya/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/amitmandliya/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/amitmandliya/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/amitmandliya/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/amitmandliya/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/amitmandliya/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
/home/amitmandliya/.local/lib/python3.7/site-packages/gym/logger.py:30: UserWarning: WARN: Box bound precision lowered by casting to float32
warnings.warn(colorize('%s: %s'%('WARN', msg % args), 'yellow'))
2020-03-21 01:24:02,468 From /home/amitmandliya/amit/multi-agent-emergence-environments/ma_policy/load_policy.py:57: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead.
2020-03-21 01:24:02,468 From /home/amitmandliya/amit/multi-agent-emergence-environments/ma_policy/load_policy.py:58: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.
2020-03-21 01:24:02,468 From /home/amitmandliya/amit/multi-agent-emergence-environments/ma_policy/load_policy.py:61: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.
2020-03-21 01:24:02.475922: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2020-03-21 01:24:02.498972: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2099940000 Hz
2020-03-21 01:24:02.499333: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x2d669a0 executing computations on platform Host. Devices:
2020-03-21 01:24:02.499353: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): <undefined>, <undefined>
Traceback (most recent call last):
File "bin/examine.py", line 91, in <module>
main()
File "/home/amitmandliya/.local/lib/python3.7/site-packages/click/core.py", line 764, in __call__
return self.main(*args, **kwargs)
File "/home/amitmandliya/.local/lib/python3.7/site-packages/click/core.py", line 717, in main
rv = self.invoke(ctx)
File "/home/amitmandliya/.local/lib/python3.7/site-packages/click/core.py", line 956, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/home/amitmandliya/.local/lib/python3.7/site-packages/click/core.py", line 555, in invoke
return callback(*args, **kwargs)
File "bin/examine.py", line 68, in main
for i, name in enumerate(policy_names)]
File "bin/examine.py", line 68, in <listcomp>
for i, name in enumerate(policy_names)]
File "/home/amitmandliya/amit/multi-agent-emergence-environments/ma_policy/load_policy.py", line 65, in load_policy
policy_fn_and_args_raw = pickle.loads(policy_dict['policy_fn_and_args'])
ModuleNotFoundError: No module named 'gym.spaces.dict_space'
Hi, thanks for releasing your whole project, I read the paper and I am quite interested in how you train your model, especially details on training buffer, however I didn't find this part in the project. Did you use an off-policy buffer to train the model?
When I examine the environment using the command bin/examine.py examples/hide_and_seek_quadrant.jsonnet examples/hide_and_seek_quadrant.npz
, I get the error below. However, when I do not specify the .npz
file, I am able to successfully visualize the environment.
(mujoco) scazlab@scazlab-INTEL:~/catkin_ws/src/multi-agent-emergence-environments$ bin/examine.py examples/hide_and_seek_quadrant.jsonnet examples/hide_and_seek_quadrant.npz
Inferred:
names: examples/hide_and_seek_quadrant.jsonnet examples/hide_and_seek_quadrant.npz
arguments: {}
2022-12-05 17:46:48.707354: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F AVX512_VNNI FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2022-12-05 17:46:48.796426: I tensorflow/core/util/port.cc:104] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2022-12-05 17:46:49.134219: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /home/scazlab/catkin_ws/devel/lib:/opt/ros/melodic/lib:/usr/local/cuda/lib64:/home/scazlab/.mujoco/mujoco210/bin:/usr/lib/nvidia
2022-12-05 17:46:49.134264: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /home/scazlab/catkin_ws/devel/lib:/opt/ros/melodic/lib:/usr/local/cuda/lib64:/home/scazlab/.mujoco/mujoco210/bin:/usr/lib/nvidia
2022-12-05 17:46:49.134269: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
Traceback (most recent call last):
File "/home/scazlab/catkin_ws/src/multi-agent-emergence-environments/bin/examine.py", line 91, in <module>
main()
File "/home/scazlab/anaconda3/envs/mujoco/lib/python3.10/site-packages/click/core.py", line 764, in __call__
return self.main(*args, **kwargs)
File "/home/scazlab/anaconda3/envs/mujoco/lib/python3.10/site-packages/click/core.py", line 717, in main
rv = self.invoke(ctx)
File "/home/scazlab/anaconda3/envs/mujoco/lib/python3.10/site-packages/click/core.py", line 956, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/home/scazlab/anaconda3/envs/mujoco/lib/python3.10/site-packages/click/core.py", line 555, in invoke
return callback(*args, **kwargs)
File "/home/scazlab/catkin_ws/src/multi-agent-emergence-environments/bin/examine.py", line 54, in main
from ma_policy.load_policy import load_policy
File "/home/scazlab/catkin_ws/src/multi-agent-emergence-environments/ma_policy/load_policy.py", line 7, in <module>
import cloudpickle as pickle
File "/home/scazlab/anaconda3/envs/mujoco/lib/python3.10/site-packages/cloudpickle/__init__.py", line 3, in <module>
from cloudpickle.cloudpickle import *
File "/home/scazlab/anaconda3/envs/mujoco/lib/python3.10/site-packages/cloudpickle/cloudpickle.py", line 151, in <module>
_cell_set_template_code = _make_cell_set_template_code()
File "/home/scazlab/anaconda3/envs/mujoco/lib/python3.10/site-packages/cloudpickle/cloudpickle.py", line 132, in _make_cell_set_template_code
return types.CodeType(
raise Exception(f'Could not find environment based on pattern {env_name}')
I want to see the latest leaderboard on this Env. Could someone guide me how to ?
OPENAI....NOT!! Low life organization..
In the line 27 of the function's comment of ma_policy.graph_construct.construct_tf_graph, I suppose it should be "Each layer spec has optional arguments: nodes_in and nodes_out" instead of "Each layer spec has optional arguments: nodes_in and nodes_in.".
When running the example code:
bin/examine.py mae_envs/envs/base.py
I get the following error:
Loading env from the module: mae_envs/envs/base.py
Creating window glfw
Traceback (most recent call last):
File "bin/examine.py", line 91, in <module>
main()
File "/home/ep15/.local/lib/python3.6/site-packages/click/core.py", line 764, in __call__
return self.main(*args, **kwargs)
File "/home/ep15/.local/lib/python3.6/site-packages/click/core.py", line 717, in main
rv = self.invoke(ctx)
File "/home/ep15/.local/lib/python3.6/site-packages/click/core.py", line 956, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/home/ep15/.local/lib/python3.6/site-packages/click/core.py", line 555, in invoke
return callback(*args, **kwargs)
File "bin/examine.py", line 47, in main
env_viewer=EnvViewer)
File "/home/ep15/libraries/mujoco-worldgen/mujoco_worldgen/util/envs/examine_env.py", line 32, in examine_env
env_viewer(env).run()
File "/home/ep15/libraries/multi-agent-emergence-environments/mae_envs/viewer/env_viewer.py", line 23, in __init__
self.env_reset()
File "/home/ep15/libraries/multi-agent-emergence-environments/mae_envs/viewer/env_viewer.py", line 59, in env_reset
self.env.reset()
File "/home/ep15/libraries/multi-agent-emergence-environments/mae_envs/wrappers/util.py", line 89, in reset
obs = self.env.reset()
File "/home/ep15/anaconda3/envs/py366_hideseek/lib/python3.6/site-packages/gym/core.py", line 259, in reset
observation = self.env.reset(**kwargs)
File "/home/ep15/anaconda3/envs/py366_hideseek/lib/python3.6/site-packages/gym/core.py", line 259, in reset
observation = self.env.reset(**kwargs)
File "/home/ep15/anaconda3/envs/py366_hideseek/lib/python3.6/site-packages/gym/core.py", line 260, in reset
return self.observation(observation)
File "/home/ep15/libraries/multi-agent-emergence-environments/mae_envs/wrappers/line_of_sight.py", line 28, in observation
self.metadata['agent_geom_idxs'][j])
File "/home/ep15/libraries/multi-agent-emergence-environments/mae_envs/util/vision.py", line 54, in insight
dist, collision_geom = raycast(sim, geom1_id, geom2_id=geom2_id, pt2=pt2)
File "/home/ep15/libraries/mujoco-worldgen/mujoco_worldgen/util/geometry.py", line 40, in raycast
dist = functions.mj_ray(sim.model,
AttributeError: 'dict2' object has no attribute 'mj_ray'
Hi,
I created a fresh python 3.6 environments and installed the dependencies from both repositories. However, when I try to unroll a saved policy in the respective environment, e.g. $ bin/examine.py examples/hide_and_seek_quadrant.jsonnet examples/hide_and_seek_quadrant.npz
, I get RuntimeError: STATIC ERROR: std.jsonnet:1249:1-5: did not expect: (IDENTIFIER, "core")
.
This might or might not be related to #19, as I am experiencing that problem as well.
Here's the full stack:
Inferred:
names: examples/hide_and_seek_full.jsonnet examples/hide_and_seek_full.npz
arguments: {}
/home/jan/.conda/envs/openairl/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:523: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/jan/.conda/envs/openairl/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:524: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/jan/.conda/envs/openairl/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/jan/.conda/envs/openairl/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/jan/.conda/envs/openairl/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/jan/.conda/envs/openairl/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:532: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
Traceback (most recent call last):
File "bin/examine.py", line 91, in <module>
main()
File "/home/jan/.conda/envs/openairl/lib/python3.6/site-packages/click/core.py", line 764, in __call__
return self.main(*args, **kwargs)
File "/home/jan/.conda/envs/openairl/lib/python3.6/site-packages/click/core.py", line 717, in main
rv = self.invoke(ctx)
File "/home/jan/.conda/envs/openairl/lib/python3.6/site-packages/click/core.py", line 956, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/home/jan/.conda/envs/openairl/lib/python3.6/site-packages/click/core.py", line 555, in invoke
return callback(*args, **kwargs)
File "bin/examine.py", line 58, in main
return_args_remaining=True, **kwargs)
File "/home/jan/Projekte/PsychoRL/mujoco-worldgen/mujoco_worldgen/util/envs/flexible_load.py", line 81, in load_env
env_data = json.loads(_jsonnet.evaluate_file(pattern))
RuntimeError: STATIC ERROR: std.jsonnet:1249:1-5: did not expect: (IDENTIFIER, "core")
I've deployed the entire environment and can play saved policies, but how do I train agents?how to produce policy ?Who can help me? I'd better have an example,thanks
Hi, I'm trying to run the example environment as specified in the doc: bin/examine.py examples/hide_and_seek_quadrant.jsonnet examples/hide_and_seek_quadrant.npz
. I've installed all the dependencies without issue. I'm not exactly sure what problem is, and I get the following output when I try running the above command:
`(rl_env) :multi-agent-emergence-environments $ bin/examine.py examples/hide_and_seek_quadrant.jsonnet examples/hide_and_seek_quadrant.npz
objc[68761]: Class GLFWApplicationDelegate is implemented in both /Users/ /.mujoco/mjpro150/bin/libglfw.3.dylib (0x10c9de778) and /usr/local/Cellar/glfw/3.3/lib/libglfw.3.3.dylib (0x10cb26710). One of the two will be used. Which one is undefined.
objc[68761]: Class GLFWWindowDelegate is implemented in both /Users/*****/.mujoco/mjpro150/bin/libglfw.3.dylib (0x10c9de700) and /usr/local/Cellar/glfw/3.3/lib/libglfw.3.3.dylib (0x10cb26738). One of the two will be used. Which one is undefined.
objc[68761]: Class GLFWContentView is implemented in both /Users/*****/.mujoco/mjpro150/bin/libglfw.3.dylib (0x10c9de7a0) and /usr/local/Cellar/glfw/3.3/lib/libglfw.3.3.dylib (0x10cb26788). One of the two will be used. Which one is undefined.
objc[68761]: Class GLFWWindow is implemented in both /Users/*****/.mujoco/mjpro150/bin/libglfw.3.dylib (0x10c9de818) and /usr/local/Cellar/glfw/3.3/lib/libglfw.3.3.dylib (0x10cb26800). One of the two will be used. Which one is undefined.
Inferred:
names: examples/hide_and_seek_quadrant.jsonnet examples/hide_and_seek_quadrant.npz
arguments: {}
WARN: <class 'mae_envs.envs.hide_and_seek.HideAndSeekRewardWrapper'> doesn't implement 'reset' method, which is required for wrappers derived directly from Wrapper. Deprecated default implementation is used.
2019-09-21 15:52:25.117396: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
Traceback (most recent call last):
File "bin/examine.py", line 91, in <module>
main()
File "//anaconda3/envs/rl_env/lib/python3.6/site-packages/click/core.py", line 764, in __call__
return self.main(*args, **kwargs)
File "//anaconda3/envs/rl_env/lib/python3.6/site-packages/click/core.py", line 717, in main
rv = self.invoke(ctx)
File "//anaconda3/envs/rl_env/lib/python3.6/site-packages/click/core.py", line 956, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "//anaconda3/envs/rl_env/lib/python3.6/site-packages/click/core.py", line 555, in invoke
return callback(*args, **kwargs)
File "bin/examine.py", line 68, in main
for i, name in enumerate(policy_names)]
File "bin/examine.py", line 68, in <listcomp>
for i, name in enumerate(policy_names)]
File "/Users/*****/Desktop/rl/multi-agent-emergence-environments/ma_policy/load_policy.py", line 73, in load_policy
policy = MAPolicy(**policy_args)
File "/Users/*****/Desktop/rl/multi-agent-emergence-environments/ma_policy/ma_policy.py", line 88, in __init__
with tf.variable_scope(self.scope, reuse=self.reuse):
File "//anaconda3/envs/rl_env/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 1980, in __enter__
return self._enter_scope_uncached()
File "//anaconda3/envs/rl_env/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 2024, in _enter_scope_uncached
current_name_scope_name = current_name_scope.__enter__()
File "//anaconda3/envs/rl_env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 6008, in __enter__
return self._name_scope.__enter__()
File "//anaconda3/envs/rl_env/lib/python3.6/contextlib.py", line 81, in __enter__
return next(self.gen)
File "//anaconda3/envs/rl_env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 4131, in name_scope
raise ValueError("'%s' is not a valid scope name" % name)
ValueError: 'policy_{i}' is not a valid scope name
`
I encounter the follwoing error when I want to run the four environments in "/multi-agent-emergence-environments-master/mae_envs/envs" folder:
running build_ext
building 'mujoco_py.cymj' extension
x86_64-linux-gnu-gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O2 -Wall -g -fstack-protector-strong -Wformat -Werror=format-security -g -fwrapv -O2 -g -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -Imujoco-py-1.50.1.0/mujoco_py -I/notebooks/mujoco-py-1.50.1.0/mujoco_py -Inotebooks/mujoco/mjpro150/include -I/usr/local/lib/python3.8/dist-packages/numpy/core/include -I/usr/include/python3.8 -c /notebooks/mujoco-py-1.50.1.0/mujoco_py/cymj.c -o /notebooks/mujoco-py-1.50.1.0/mujoco_py/generated/_pyxbld_LinuxCPUExtensionBuilder/temp.linux-x86_64-3.8/notebooks/mujoco-py-1.50.1.0/mujoco_py/cymj.o -fopenmp -w
/notebooks/mujoco-py-1.50.1.0/mujoco_py/cymj.c:666:10: fatal error: mjmodel.h: No such file or directory
666 | #include "mjmodel.h"
| ^~~~~~~~~~~
compilation terminated.
Traceback (most recent call last):
File "/usr/lib/python3.8/distutils/unixccompiler.py", line 117, in _compile
self.spawn(compiler_so + cc_args + [src, '-o', obj] +
File "/usr/lib/python3.8/distutils/ccompiler.py", line 910, in spawn
spawn(cmd, dry_run=self.dry_run)
File "/usr/lib/python3.8/distutils/spawn.py", line 36, in spawn
_spawn_posix(cmd, search_path, dry_run=dry_run)
File "/usr/lib/python3.8/distutils/spawn.py", line 157, in _spawn_posix
raise DistutilsExecError(
distutils.errors.DistutilsExecError: command 'x86_64-linux-gnu-gcc' failed with exit status 1
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "multi-agent-emergence-environments-master/mae_envs/envs/blueprint_construction.py", line 5, in
from mae_envs.wrappers.util import (DiscretizeActionWrapper, MaskActionWrapper,
File "/notebooks/multi-agent-emergence-environments-master/mae_envs/wrappers/util.py", line 2, in
from mujoco_py import MujocoException
File "/notebooks/mujoco-py-1.50.1.0/mujoco_py/init.py", line 1, in
from mujoco_py.builder import cymj, ignore_mujoco_warnings, functions, MujocoException
File "/notebooks/mujoco-py-1.50.1.0/mujoco_py/builder.py", line 283, in
cymj = load_cython_ext(mjpro_path)
File "/notebooks/mujoco-py-1.50.1.0/mujoco_py/builder.py", line 54, in load_cython_ext
cext_so_path = builder.build()
File "/notebooks/mujoco-py-1.50.1.0/mujoco_py/builder.py", line 131, in build
dist.run_commands()
File "/usr/lib/python3.8/distutils/dist.py", line 966, in run_commands
self.run_command(cmd)
File "/usr/lib/python3.8/distutils/dist.py", line 985, in run_command
cmd_obj.run()
File "/usr/local/lib/python3.8/dist-packages/Cython/Distutils/old_build_ext.py", line 186, in run
_build_ext.build_ext.run(self)
File "/usr/lib/python3.8/distutils/command/build_ext.py", line 340, in run
self.build_extensions()
File "/notebooks/mujoco-py-1.50.1.0/mujoco_py/builder.py", line 75, in build_extensions
build_ext.build_extensions(self)
File "/usr/local/lib/python3.8/dist-packages/Cython/Distutils/old_build_ext.py", line 195, in build_extensions
_build_ext.build_ext.build_extensions(self)
File "/usr/lib/python3.8/distutils/command/build_ext.py", line 449, in build_extensions
self._build_extensions_serial()
File "/usr/lib/python3.8/distutils/command/build_ext.py", line 474, in _build_extensions_serial
self.build_extension(ext)
File "/usr/lib/python3.8/distutils/command/build_ext.py", line 528, in build_extension
objects = self.compiler.compile(sources,
File "/usr/lib/python3.8/distutils/ccompiler.py", line 574, in compile
self._compile(obj, src, ext, cc_args, extra_postargs, pp_opts)
File "/usr/lib/python3.8/distutils/unixccompiler.py", line 120, in _compile
raise CompileError(msg)
distutils.errors.CompileError: command 'x86_64-linux-gnu-gcc' failed with exit status 1
"mjmodel.h" is already in "/mujoco/mjpro/include/mjmodel.h". So my question is that most probably the environment files or more specifically "cymj.c" is not able to find "mjmodel.h" due to some problem in installation, or is there any other reason? Thanks!
Sorry, I am a beginner, I just want to reproduce this paper, I run bin/examine.py examples/hide_and_seek_quadrant.jsonnet examples/hide_and_seek_quadrant.npz
, and the result has been stopped here
(base) root@lang:~/Downloads/multi-agent-emergence-environments# bin/examine.py examples/hide_and_seek_quadrant.jsonnet examples/hide_and_seek_quadrant.npz
Inferred:
names: examples/hide_and_seek_quadrant.jsonnet examples/hide_and_seek_quadrant.npz
arguments: {}
2020-07-06 10:14:55.019859: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2020-07-06 10:14:55.060290: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 2599990000 Hz
2020-07-06 10:14:55.061626: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f24a4000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-07-06 10:14:55.061723: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
2020-07-06 10:14:55.070895: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1
, I do not know what to do next, can get a little help, I will be grateful
My system environment information:
(base) root@lang:~# uname -a
Linux lang 5.7.0-kali1-amd64 #1 SMP Debian 5.7.6-1kali2 (2020-07-01) x86_64 GNU/Linux
(base) root@lang:~# nvidia-smi
Mon Jul 6 11:31:47 2020
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 440.100 Driver Version: 440.100 CUDA Version: 10.2 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce GTX 960M Off | 00000000:01:00.0 Off | N/A |
| N/A 72C P0 N/A / N/A | 11MiB / 4046MiB | 100% Default |
(base) root@lang:~# python --version
Python 3.7.3
and I run it in Pycharm
I want it to support tf2, but I ran into some problems:
gym.error.DoubleWrapperError: Attempted to double wrap with Wrapper: AgentGeomObsMask2D
### Environment:
(env1) root@agi:/home/agi/Downloads/multi-agent-emergence-environments# uname -a
Linux agi 5.13.0-22-generic #22-Ubuntu SMP Fri Nov 5 13:21:36 UTC 2021 x86_64 x86_64 x86_64 GNU/Linux
(env1) root@agi:/home/agi/Downloads/multi-agent-emergence-environments# conda list
# packages in environment at /root/anaconda3/envs/env1:
#
# Name Version Build Channel
_libgcc_mutex 0.1 conda_forge conda-forge
_openmp_mutex 4.5 1_gnu conda-forge
_tflow_select 2.1.0 gpu
abseil-cpp 20210324.2 h9c3ff4c_0 conda-forge
absl-py 1.0.0 pyhd8ed1ab_0 conda-forge
aiohttp 3.8.1 py39h3811e60_0 conda-forge
aiosignal 1.2.0 pyhd8ed1ab_0 conda-forge
alabaster 0.7.12 py_0 conda-forge
astor 0.8.1 pyh9f0ad1d_0 conda-forge
astunparse 1.6.3 pyhd8ed1ab_0 conda-forge
async-timeout 4.0.1 pyhd8ed1ab_0 conda-forge
attrs 21.2.0 pyhd8ed1ab_0 conda-forge
babel 2.9.1 pyh44b312d_0 conda-forge
backcall 0.2.0 pyh9f0ad1d_0 conda-forge
backports 1.0 py_2 conda-forge
backports.functools_lru_cache 1.6.4 pyhd8ed1ab_0 conda-forge
baselines 0.1.6 dev_0 <develop>
binutils_impl_linux-64 2.36.1 h193b22a_2 conda-forge
blinker 1.4 py_1 conda-forge
brotlipy 0.7.0 py39h3811e60_1003 conda-forge
c-ares 1.18.1 h7f98852_0 conda-forge
ca-certificates 2021.10.26 h06a4308_2
cachetools 4.2.4 pyhd8ed1ab_0 conda-forge
certifi 2021.10.8 py39h06a4308_0
cffi 1.15.0 pypi_0 pypi
charset-normalizer 2.0.7 pyhd8ed1ab_0 conda-forge
click 8.0.3 py39hf3d152e_1 conda-forge
cloudpickle 1.2.2 pypi_0 pypi
colorama 0.4.4 pyh9f0ad1d_0 conda-forge
cryptography 36.0.0 py39h95dcef6_0 conda-forge
cudatoolkit 11.3.1 h2bc3f7f_2
cudnn 8.2.1 cuda11.3_0
cython 0.29.24 py39he80948d_1 conda-forge
dataclasses 0.8 pyhc8e2a94_3 conda-forge
decorator 5.1.0 pyhd8ed1ab_0 conda-forge
docutils 0.17.1 pypi_0 pypi
fasteners 0.16.3 pypi_0 pypi
freetype 2.10.4 h0708190_1 conda-forge
frozenlist 1.2.0 py39h3811e60_1 conda-forge
future 0.18.2 pypi_0 pypi
gast 0.3.3 py_0 conda-forge
gcc 11.2.0 h702ea55_1 conda-forge
gcc_impl_linux-64 11.2.0 h82a94d6_11 conda-forge
giflib 5.2.1 h36c2ea0_2 conda-forge
glfw 2.4.0 pypi_0 pypi
google-auth 1.35.0 pyh6c4a22f_0 conda-forge
google-auth-oauthlib 0.4.6 pyhd8ed1ab_0 conda-forge
google-pasta 0.2.0 pyh8c360ce_0 conda-forge
grpc-cpp 1.37.1 hfc4d69e_3 conda-forge
grpcio 1.37.1 py39hff7568b_0 conda-forge
gym 0.10.5 pypi_0 pypi
h5py 2.10.0 nompi_py39h98ba4bc_106 conda-forge
hdf5 1.10.6 nompi_h6a2412b_1114 conda-forge
icu 68.2 h9c3ff4c_0 conda-forge
idna 3.3 pypi_0 pypi
imagehash 4.2.1 pyhd8ed1ab_0 conda-forge
imageio 2.11.1 pypi_0 pypi
imagesize 1.3.0 pyhd8ed1ab_0 conda-forge
importlib-metadata 4.8.2 py39hf3d152e_0 conda-forge
iniconfig 1.1.1 pyh9f0ad1d_0 conda-forge
ipdb 0.13.9 pyhd8ed1ab_0 conda-forge
ipython 7.29.0 py39hef51801_2 conda-forge
jbig 2.1 h7f98852_2003 conda-forge
jedi 0.18.1 py39hf3d152e_0 conda-forge
jinja2 3.0.3 pyhd8ed1ab_0 conda-forge
joblib 1.1.0 pypi_0 pypi
jpeg 9d h36c2ea0_0 conda-forge
jsonnet 0.17.0 pypi_0 pypi
keras 2.7.0 pypi_0 pypi
keras-preprocessing 1.1.2 pyhd8ed1ab_0 conda-forge
kernel-headers_linux-64 2.6.32 he073ed8_15 conda-forge
krb5 1.19.2 hcc1bbae_3 conda-forge
lcms2 2.12 hddcbb42_0 conda-forge
ld_impl_linux-64 2.36.1 hea4e1c9_2 conda-forge
lerc 2.2.1 h9c3ff4c_0 conda-forge
libblas 3.9.0 12_linux64_openblas conda-forge
libcblas 3.9.0 12_linux64_openblas conda-forge
libclang 12.0.0 pypi_0 pypi
libcurl 7.79.1 h2574ce0_1 conda-forge
libdeflate 1.7 h7f98852_5 conda-forge
libedit 3.1.20210910 h7f8727e_0
libev 4.33 h516909a_1 conda-forge
libffi 3.3 he6710b0_2
libgcc-devel_linux-64 11.2.0 h0952999_11 conda-forge
libgcc-ng 11.2.0 h1d223b6_11 conda-forge
libgfortran-ng 11.2.0 h69a702a_11 conda-forge
libgfortran5 11.2.0 h5c6108e_11 conda-forge
libgomp 11.2.0 h1d223b6_11 conda-forge
liblapack 3.9.0 12_linux64_openblas conda-forge
libnghttp2 1.43.0 h812cca2_1 conda-forge
libopenblas 0.3.18 pthreads_h8fe5266_0 conda-forge
libpng 1.6.37 h21135ba_2 conda-forge
libprotobuf 3.15.8 h780b84a_1 conda-forge
libsanitizer 11.2.0 he4da1e4_11 conda-forge
libssh2 1.10.0 ha56f1ee_2 conda-forge
libstdcxx-ng 11.2.0 he4da1e4_11 conda-forge
libtiff 4.3.0 hf544144_1 conda-forge
libwebp-base 1.2.1 h7f98852_0 conda-forge
libxcb 1.13 h7f98852_1004 conda-forge
lockfile 0.12.2 py_1 conda-forge
lz4-c 1.9.3 h9c3ff4c_1 conda-forge
markdown 3.3.6 pyhd8ed1ab_0 conda-forge
markupsafe 2.0.1 py39h3811e60_1 conda-forge
matplotlib-inline 0.1.3 pyhd8ed1ab_0 conda-forge
monotonic 1.5 py_0 conda-forge
more-itertools 8.12.0 pyhd8ed1ab_0 conda-forge
mujoco-py 2.0.2.13 dev_0 <develop>
mujoco-worldgen 0.0.0 dev_0 <develop>
multidict 5.2.0 py39h3811e60_1 conda-forge
ncurses 6.3 h7f8727e_2
numpy 1.21.0 pypi_0 pypi
numpy-stl 2.16.3 pypi_0 pypi
oauthlib 3.1.1 pyhd8ed1ab_0 conda-forge
olefile 0.46 pyh9f0ad1d_1 conda-forge
opencv-python 4.5.4.60 pypi_0 pypi
openssl 1.1.1l h7f8727e_0
opt_einsum 3.3.0 pyhd8ed1ab_1 conda-forge
p5py 1.0.0 pypi_0 pypi
packaging 21.3 pyhd8ed1ab_0 conda-forge
parso 0.8.2 pyhd8ed1ab_0 conda-forge
pep517 0.12.0 pypi_0 pypi
pexpect 4.8.0 pyh9f0ad1d_2 conda-forge
pickleshare 0.7.5 py_1003 conda-forge
pillow 8.4.0 pypi_0 pypi
pip 21.3.1 pypi_0 pypi
pluggy 1.0.0 py39hf3d152e_2 conda-forge
prompt-toolkit 3.0.22 pyha770c72_0 conda-forge
protobuf 3.15.8 py39he80948d_0 conda-forge
pthread-stubs 0.4 h36c2ea0_1001 conda-forge
ptyprocess 0.7.0 pyhd3deb0d_0 conda-forge
py 1.11.0 pyh6c4a22f_0 conda-forge
pyasn1 0.4.8 py_0 conda-forge
pyasn1-modules 0.2.7 py_0 conda-forge
pycparser 2.21 pyhd8ed1ab_0 conda-forge
pyglet 1.5.0 pypi_0 pypi
pygments 2.10.0 pyhd8ed1ab_0 conda-forge
pyjwt 2.0.1 pyhd8ed1ab_0 conda-forge
pyopenssl 21.0.0 pyhd8ed1ab_0 conda-forge
pyparsing 3.0.6 pyhd8ed1ab_0 conda-forge
pysocks 1.7.1 py39hf3d152e_4 conda-forge
pytest 6.2.5 pypi_0 pypi
pytest-instafail 0.4.2 pypi_0 pypi
python 3.9.7 h12debd9_1
python-flatbuffers 1.12 pyhd8ed1ab_1 conda-forge
python-utils 2.5.6 pypi_0 pypi
python_abi 3.9 2_cp39 conda-forge
pytz 2021.3 pyhd8ed1ab_0 conda-forge
pyu2f 0.1.5 pyhd8ed1ab_0 conda-forge
pywavelets 1.2.0 py39hce5d2b2_0 conda-forge
re2 2021.08.01 h9c3ff4c_0 conda-forge
readline 8.1 h27cfd23_0
requests 2.26.0 pyhd8ed1ab_1 conda-forge
requests-oauthlib 1.3.0 pyh9f0ad1d_0 conda-forge
rsa 4.8 pyhd8ed1ab_0 conda-forge
scipy 1.7.2 pypi_0 pypi
setuptools 59.4.0 pypi_0 pypi
six 1.16.0 pyh6c4a22f_0 conda-forge
snappy 1.1.8 he1b5a44_3 conda-forge
snowballstemmer 2.2.0 pyhd8ed1ab_0 conda-forge
sphinx 4.3.0 pyh6c4a22f_0 conda-forge
sphinx_rtd_theme 1.0.0 pyhd8ed1ab_0 conda-forge
sphinxcontrib-applehelp 1.0.2 py_0 conda-forge
sphinxcontrib-devhelp 1.0.2 py_0 conda-forge
sphinxcontrib-htmlhelp 2.0.0 pyhd8ed1ab_0 conda-forge
sphinxcontrib-jsmath 1.0.1 py_0 conda-forge
sphinxcontrib-qthelp 1.0.3 py_0 conda-forge
sphinxcontrib-serializinghtml 1.1.5 pyhd8ed1ab_1 conda-forge
sqlite 3.36.0 hc218d9a_0
sysroot_linux-64 2.12 he073ed8_15 conda-forge
tensorboard 2.7.0 pypi_0 pypi
tensorboard-data-server 0.6.1 pypi_0 pypi
tensorboard-plugin-wit 1.8.0 pyh44b312d_0 conda-forge
tensorflow 2.4.1 py39hf3d152e_0 conda-forge
tensorflow-base 2.4.1 py39h23a8cbf_0 conda-forge
tensorflow-estimator 2.7.0 pypi_0 pypi
tensorflow-gpu 2.7.0 pypi_0 pypi
tensorflow-io-gcs-filesystem 0.22.0 pypi_0 pypi
termcolor 1.1.0 py_2 conda-forge
tk 8.6.11 h1ccaba5_0
toml 0.10.2 pyhd8ed1ab_0 conda-forge
tomli 1.2.2 pypi_0 pypi
tqdm 4.62.3 pypi_0 pypi
traitlets 5.1.1 pyhd8ed1ab_0 conda-forge
typing-extensions 4.0.0 hd8ed1ab_0 conda-forge
typing_extensions 4.0.0 pyha770c72_0 conda-forge
tzdata 2021e hda174b7_0
urllib3 1.26.7 pyhd8ed1ab_0 conda-forge
wcwidth 0.2.5 pyh9f0ad1d_2 conda-forge
werkzeug 2.0.1 pyhd8ed1ab_0 conda-forge
wheel 0.37.0 pyhd3eb1b0_1
wrapt 1.13.3 py39h3811e60_1 conda-forge
xmltodict 0.12.0 pypi_0 pypi
xorg-fixesproto 5.0 h7f98852_1002 conda-forge
xorg-kbproto 1.0.7 h7f98852_1002 conda-forge
xorg-libx11 1.7.2 h7f98852_0 conda-forge
xorg-libxau 1.0.9 h7f98852_0 conda-forge
xorg-libxcursor 1.2.0 h7f98852_0 conda-forge
xorg-libxdmcp 1.1.3 h7f98852_0 conda-forge
xorg-libxext 1.3.4 h7f98852_1 conda-forge
xorg-libxfixes 5.0.3 h7f98852_1004 conda-forge
xorg-libxinerama 1.1.4 h9c3ff4c_1001 conda-forge
xorg-libxrandr 1.5.2 h7f98852_1 conda-forge
xorg-libxrender 0.9.10 h7f98852_1003 conda-forge
xorg-randrproto 1.5.0 h7f98852_1001 conda-forge
xorg-renderproto 0.11.1 h7f98852_1002 conda-forge
xorg-xextproto 7.3.0 h7f98852_1002 conda-forge
xorg-xproto 7.0.31 h7f98852_1007 conda-forge
xz 5.2.5 h7b6447c_0
yarl 1.7.2 py39h3811e60_1 conda-forge
zipp 3.6.0 pyhd8ed1ab_0 conda-forge
zlib 1.2.11 h7b6447c_3
zstd 1.5.0 ha95c52a_0 conda-forge
(env1) root@agi:/home/agi/Downloads/multi-agent-emergence-environments# pip3 list
Package Version Location
----------------------------- --------- ----------------------------------------------------------------------------------
absl-py 1.0.0
aiohttp 3.8.1
aiosignal 1.2.0
alabaster 0.7.12
astor 0.8.1
astunparse 1.6.3
async-timeout 4.0.1
attrs 21.2.0
Babel 2.9.1
backcall 0.2.0
backports.functools-lru-cache 1.6.4
baselines 0.1.6 /home/agi/Downloads/baselines
blinker 1.4
brotlipy 0.7.0
cachetools 4.2.4
certifi 2021.10.8
cffi 1.15.0
charset-normalizer 2.0.7
click 8.0.3
cloudpickle 1.2.2
colorama 0.4.4
cryptography 36.0.0
Cython 0.29.24
dataclasses 0.8
decorator 5.1.0
docutils 0.17.1
fasteners 0.16.3
flatbuffers 1.12
frozenlist 1.2.0
future 0.18.2
gast 0.3.3
glfw 2.4.0
google-auth 1.35.0
google-auth-oauthlib 0.4.6
google-pasta 0.2.0
grpcio 1.37.1
gym 0.10.5
h5py 2.10.0
idna 3.3
ImageHash 4.2.1
imageio 2.11.1
imagesize 1.3.0
importlib-metadata 4.8.2
iniconfig 1.1.1
ipdb 0.13.9
ipython 7.29.0
jedi 0.18.1
Jinja2 3.0.3
joblib 1.1.0
jsonnet 0.17.0
keras 2.7.0
Keras-Preprocessing 1.1.2
libclang 12.0.0
lockfile 0.12.2
Markdown 3.3.6
MarkupSafe 2.0.1
matplotlib-inline 0.1.3
monotonic 1.5
more-itertools 8.12.0
mujoco-py 2.0.2.13 /root/anaconda3/envs/env1/lib/python3.9/site-packages/mujoco_py-2.0.2.13-py3.9.egg
mujoco-worldgen 0.0.0 /home/agi/Downloads/mujoco-worldgen
multidict 5.2.0
numpy 1.21.4
numpy-stl 2.16.3
oauthlib 3.1.1
olefile 0.46
opencv-python 4.5.4.60
opt-einsum 3.3.0
p5py 1.0.0
packaging 21.3
parso 0.8.2
pep517 0.12.0
pexpect 4.8.0
pickleshare 0.7.5
Pillow 8.4.0
pip 21.3.1
pluggy 1.0.0
prompt-toolkit 3.0.22
protobuf 3.15.8
ptyprocess 0.7.0
py 1.11.0
pyasn1 0.4.8
pyasn1-modules 0.2.7
pycparser 2.21
pyglet 1.5.0
Pygments 2.10.0
PyJWT 2.0.1
pyOpenSSL 21.0.0
pyparsing 3.0.6
PySocks 1.7.1
pytest 6.2.5
pytest-instafail 0.4.2
python-utils 2.5.6
pytz 2021.3
pyu2f 0.1.5
PyWavelets 1.2.0
requests 2.26.0
requests-oauthlib 1.3.0
rsa 4.8
scipy 1.7.3
setuptools 59.4.0
six 1.16.0
snowballstemmer 2.2.0
Sphinx 4.3.0
sphinx-rtd-theme 1.0.0
sphinxcontrib-applehelp 1.0.2
sphinxcontrib-devhelp 1.0.2
sphinxcontrib-htmlhelp 2.0.0
sphinxcontrib-jsmath 1.0.1
sphinxcontrib-qthelp 1.0.3
sphinxcontrib-serializinghtml 1.1.5
tensorboard 2.7.0
tensorboard-data-server 0.6.1
tensorboard-plugin-wit 1.8.0
tensorflow 2.4.1
tensorflow-estimator 2.7.0
tensorflow-gpu 2.7.0
tensorflow-io-gcs-filesystem 0.22.0
termcolor 1.1.0
toml 0.10.2
tomli 1.2.2
tqdm 4.62.3
traitlets 5.1.1
typing_extensions 4.0.0
urllib3 1.26.7
wcwidth 0.2.5
Werkzeug 2.0.1
wheel 0.37.0
wrapt 1.13.3
xmltodict 0.12.0
yarl 1.7.2
zipp 3.6.0
Hi! I read the paper and follow the Transformer architecture etc.
( As noted below, some behavior seems only discoverable by randomly finding it. )
I have an idea how the bots are learning. First, I noticed each team takes a turn at finding a solution. It takes many games. Then, the next team finds their solution next. This looks like a step-by-step learning. Where they are randomly moving and hit a solution. But it's not full brute-force, they take random actions and many are a solution, and the attention/etc aids, making it a partial-brute force? I noticed the bots move/grab perfectly just in time, and they start off randomly moving around but learn what to keep doing and what to add on to their plan. It seems progressive and seems like it is something simpler going on.
Take for example the way at final stage the one blue hider moved the box in position *for the other team member for when he arrived back it would be closer. Why? It must had randomly tried actions, and found what worked in its super short time limit. What aided it I'm assuming is Attention, but I wonder why...how would Attention help it take better random actions?
For example, it needs to pull in the ramp so they can't jump over the wall... what tells only 1 blue hider to go to the other side of the room and where to bring it!? This looks like a brute force/normal RL. I don't see how the attention/sensor RNN thingy is aiding the solution finding to occur quicker.
P.S. What about only 1 team in a rain-forest that has to avoid rain entering the hut they need to stay in? Same thing but the environment is the seekers/eaters instead of needing other agents to find/eat/end them.
I also like how yous skipped learning to crawl/run/grab, just like skipping simulating atoms and aiming for high-level water simulation.
When running an example like bin/examine.py examples/hide_and_seek_quadrant.jsonnet examples/hide_and_seek_quadrant.npz
gcc errors with cymj.o: file not recognized: file format not recognized
This depends on the proprietary MuJoCo physics engine, which apparently requires a subscription-based license for extended use. So would it be feasible to eliminate this dependency and replace it with something else? A free, open-source physics engine would be ideal, but even one that's just free as in beer (without any trial period or student requirement) would be a great improvement.
I know the readme says this repository is no longer being updated, but hopefully there's someone (from OpenAI or otherwise) who would be interested in taking this on as a project.
Hey, I would like to implement some different policies to play the game, and I am trying to find out the meanings of the variables in the observations. Could you elaborate a little bit on the parameters in 'observation_self'? Thank you kindly for your attention.
Hello, everyone! If you are interested in developing your own projects with the multi-agent-emergence-environments by OpenAI but is having a hard time wrapping your head around the existing code (like I did myself for at least a couple of weeks!), please feel free to take a look at a project I developed at ETH Zürich using multi-agent-emergence-environments. It is called "Cooperation Learning for multi-agent systems", and you can find its repository at https://github.com/leonardovvla/multi-agent-cooperation-learning. Hope it can be helpful to at least some of you! All the best!
Hi,
i was wondering if it is possible to use this repository in order to render the simulations as you show in your blog (better looking characters, obstacles, floors, etc.)?
when i ran the examine.py script the render of the env was rather basic..
thanks
Whenever I try to run the environments such as base or hide_and_seek through the
bin/examine.py hide_and_seek or base commands
I receive this error:
Inferred:
names: hide_and_seek.py
arguments: {}
Traceback (most recent call last):
File "bin/examine.py", line 91, in <module>
main()
File "/home/avi/anaconda3/envs/python3.6/lib/python3.6/site-packages/click/core.py", line 764, in __call__
return self.main(*args, **kwargs)
File "/home/avi/anaconda3/envs/python3.6/lib/python3.6/site-packages/click/core.py", line 717, in main
rv = self.invoke(ctx)
File "/home/avi/anaconda3/envs/python3.6/lib/python3.6/site-packages/click/core.py", line 956, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/home/avi/anaconda3/envs/python3.6/lib/python3.6/site-packages/click/core.py", line 555, in invoke
return callback(*args, **kwargs)
File "bin/examine.py", line 47, in main
env_viewer=EnvViewer)
File "/home/avi/Desktop/hideandseek/mujoco-worldgen/mujoco_worldgen/util/envs/examine_env.py", line 26, in examine_env
return_args_remaining=True, **env_kwargs)
File "/home/avi/Desktop/hideandseek/mujoco-worldgen/mujoco_worldgen/util/envs/flexible_load.py", line 88, in load_env
matching = (glob(join(core_dir, envs_dir, "**", "*.py"), recursive=True) +
File "/home/avi/anaconda3/envs/python3.6/lib/python3.6/posixpath.py", line 94, in join
genericpath._check_arg_types('join', a, *p)
File "/home/avi/anaconda3/envs/python3.6/lib/python3.6/genericpath.py", line 149, in _check_arg_types
(funcname, s.__class__.__name__)) from None
TypeError: join() argument must be str or bytes, not 'tuple'
I'm not sure how to fix it and running the environments with the pre-trained models works perfectly fine.
How does the policy know whether the observation is from hider or seekers?
How do i run the project so that I can see the agents doing the work?
I can't find any scenes in the project
Finally, after installed all the related package and applying the license, Segmentation error shows up.
Does anybody know about the memory requirement of running this project?
My current memory is 4 GB. Is it too small?
Thank you.
Thanks for releasing your whole project,but I can't find the trainning progress. I want to know about rapid architecture, can you give me some information?
ma_policy/graph_construct.py specifies that file mas/ppo/base-architectures.jsonnet contains example architectures, to the best of my ability I can't find that file in the repository.
When i run
pip install -e multi-agent-emergence-environments/
The following error appears:
Running setup.py develop for mae-envs
ERROR: Command errored out with exit status 1:
command: /home/jtr/anaconda3/envs/mujoco/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/home/jtr/multi-agent-emergence-environments/setup.py'"'"'; file='"'"'/home/jtr/multi-agent-emergence-environments/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(file);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, file, '"'"'exec'"'"'))' develop --no-deps
cwd: /home/jtr/multi-agent-emergence-environments/
Complete output (3 lines):
running develop
running egg_info
error: [Errno 13] Permission denied
ERROR: Command errored out with exit status 1: /home/jtr/anaconda3/envs/mujoco/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/home/jtr/multi-agent-emergence-environments/setup.py'"'"'; file='"'"'/home/jtr/multi-agent-emergence-environments/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(file);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, file, '"'"'exec'"'"'))' develop --no-deps Check the logs for full command output.
I thought it was not enough authority, so I executed:
sudo pip install -e multi-agent-emergence-environments/
The output seems to be successful, but mae-envs cannot be found when running base.
No handlers could be found for logger "pip._internal.network.auth"
DEPRECATION: Python 2.7 reached the end of its life on January 1st, 2020. Please upgrade your Python as Python 2.7 is no longer maintained. pip 21.0 will drop support for Python 2.7 in January 2021. More details about Python 2 support in pip, can be found at https://pip.pypa.io/en/latest/development/release-process/#python-2-support
WARNING: The directory '/home/jtr/.cache/pip' or its parent directory is not owned or is not writable by the current user. The cache has been disabled. Check the permissions and owner of that directory. If executing pip with sudo, you may want sudo's -H flag.
Looking in indexes: http://pypi.douban.com/simple
Obtaining file:///home/jtr/multi-agent-emergence-environments
Installing collected packages: mae-envs
Attempting uninstall: mae-envs
Found existing installation: mae-envs 0.0.0
Uninstalling mae-envs-0.0.0:
Successfully uninstalled mae-envs-0.0.0
Running setup.py develop for mae-envs
Successfully installed mae-envs
So did I install it successfully? In addition, how to test after successful installation
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.