improbable-ai / rapid-locomotion-rl Goto Github PK

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 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 "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