improbable-ai / rapid-locomotion-rl Goto Github PK
View Code? Open in Web Editor NEWCode for Rapid Locomotion via Reinforcement Learning
License: Other
Code for Rapid Locomotion via Reinforcement Learning
License: Other
Thanks for sharing your code!!
When I run python scripts/test.py
to verify the installation, the following error message appears.
.../mini_gym/envs/base/legged_robot.py:1033: DeprecationWarning:
np.int
is a deprecated alias for the builtinint
. To silence this warning, useint
by itself. Doing this will not modify any behavior and is safe. When replacingnp.int
, you may wish to use e.g.np.int64
ornp.int32
to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
self.env_command_bins = np.zeros(len(env_ids), dtype=np.int)
Traceback (most recent call last):
File "scripts/test.py", line 50, in
run_env(render=True, headless=False)
File "scripts/test.py", line 31, in run_env
env = gym.make("VelocityTrackingEasyEnv-v0", headless=headless, cfg=Cfg)
File ".../lib/python3.8/site-packages/gym/envs/registration.py", line 601, in make
env = PassiveEnvChecker(env)
File ".../lib/python3.8/site-packages/gym/wrappers/env_checker.py", line 22, in init
assert hasattr(
AssertionError: You must specify a action space. https://www.gymlibrary.ml/content/environment_creation/_
I have confirmed that the isaac gym is well installed.
Have you ever experienced or solved this problem?
Thanks.
Thanks for the code!
When I was verifying the installation and run python scripts/test.py, the following error appears.
DeprecationWarning: np.int
is a deprecated alias for the builtin int
. To silence this warning, use int
by itself. Doing this will not modify any behavior and is safe. When replacing np.int
, you may wish to use e.g. np.int64
or np.int32
to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
self.env_command_bins = np.zeros(len(env_ids), dtype=np.int)
Traceback (most recent call last):
File "../anaconda3/envs/rlgym/lib/python3.8/site-packages/params_proto/neo_proto.py", line 168, in getattribute
value = get_hooks[-1](self, item)
IndexError: tuple index out of range
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "scripts/test.py", line 51, in
run_env(render=True, headless=True)
File "scripts/test.py", line 31, in run_env
env = gym.make("VelocityTrackingEasyEnv-v0", headless=render and not headless, cfg=Cfg)
File "../anaconda3/envs/rlgym/lib/python3.8/site-packages/gym/envs/registration.py", line 592, in make
env = env_creator(**_kwargs)
File "../rapid-locomotion-rl-2/mini_gym/envs/mini_cheetah/velocity_tracking/velocity_tracking_easy_env.py", line 39, in init
super().init(cfg, sim_params, physics_engine, sim_device, headless, eval_cfg, initial_dynamics_dict)
File "../rapid-locomotion-rl-2/mini_gym/envs/base/legged_robot.py", line 51, in init
self._init_buffers()
File "../rapid-locomotion-rl-2/mini_gym/envs/base/legged_robot.py", line 955, in _init_buffers
self.noise_scale_vec = self._get_noise_scale_vec(self.cfg) # , self.eval_cfg)
File "../rapid-locomotion-rl-2/mini_gym/envs/base/legged_robot.py", line 884, in _get_noise_scale_vec
if self.cfg.env.observe_height_command:
File "../anaconda3/envs/rlgym/lib/python3.8/site-packages/params_proto/neo_proto.py", line 171, in getattribute
value = type.getattribute(self, item)
AttributeError: type object 'env' has no attribute 'observe_height_command'
Hi,
I would like to test the implementation of your methodology on UnitreeA1 and would like to know what is your preferred way of converting the XML files at (https://github.com/unitreerobotics/unitree_mujoco/tree/main/data/a1) to get this repo simulation going.
Thank you,
Sanket
When i run "python scripts/test.py", an error arised!
Traceback (most recent call last):
File "scripts/test.py", line 13, in
from mini_gym.envs.base.legged_robot_config import Cfg
File "/home/yfy/Quadruped/rapid-locomotion-rl-main/mini_gym/envs/base/legged_robot_config.py", line 4, in
from params_proto.neo_proto import PrefixProto, ParamsProto
ModuleNotFoundError: No module named 'params_proto.neo_proto'
When I tried to use the IsaacGym_Preview_4, this error occured.
File "scripts/test.py", line 51, in <module>
run_env(render=True, headless=False)
File "scripts/test.py", line 32, in run_env
env = VelocityTrackingEasyEnv(sim_device='cuda:0', headless=False, cfg=Cfg)
File "/home/user/rl/rapid-locomotion-rl/mini_gym/envs/mini_cheetah/velocity_tracking/velocity_tracking_easy_env.py", line 38, in __init__
gymutil.parse_sim_config(vars(cfg.sim), sim_params)
File "/home/user/isaacgym/python/isaacgym/gymutil.py", line 407, in parse_sim_config
parse_physx_config(sim_cfg["physx"], sim_options)
File "/home/user/isaacgym/python/isaacgym/gymutil.py", line 438, in parse_physx_config
parse_float_int_bool(physx_cfg, sim_options.physx, params)
File "/home/user/isaacgym/python/isaacgym/gymutil.py", line 448, in parse_float_int_bool
if opt in cfg:
TypeError: argument of type 'Meta' is not iterable
It seems that the type of the cfg can't match.
Have you used the isaacgym4 for the gym training?
And how you solved this kind of errors?
Updates of params_proto breaks dependency requirements, you should specify version==2.10.0
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.