How to train multiple environments with RL in one scene at the same time?

Hello! I tried change the value of ‘self.num_envs’ in the example ‘cartpole_task.py’.But it didn’t work.

Traceback (most recent call last):
  File "cartpole_example.py", line 26, in <module>
    model.learn(total_timesteps=100000)
  File "/media/lyc/files/U_omniverse/pkg/isaac_sim-2022.1.0/kit/python/lib/python3.7/site-packages/stable_baselines3/ppo/ppo.py", line 313, in learn
    reset_num_timesteps=reset_num_timesteps,
  File "/media/lyc/files/U_omniverse/pkg/isaac_sim-2022.1.0/kit/python/lib/python3.7/site-packages/stable_baselines3/common/on_policy_algorithm.py", line 243, in learn
    total_timesteps, eval_env, callback, eval_freq, n_eval_episodes, eval_log_path, reset_num_timesteps, tb_log_name
  File "/media/lyc/files/U_omniverse/pkg/isaac_sim-2022.1.0/kit/python/lib/python3.7/site-packages/stable_baselines3/common/base_class.py", line 429, in _setup_learn
    self._last_obs = self.env.reset()  # pytype: disable=annotation-type-mismatch
  File "/media/lyc/files/U_omniverse/pkg/isaac_sim-2022.1.0/kit/python/lib/python3.7/site-packages/stable_baselines3/common/vec_env/dummy_vec_env.py", line 61, in reset
    obs = self.envs[env_idx].reset()
  File "/media/lyc/files/U_omniverse/pkg/isaac_sim-2022.1.0/kit/python/lib/python3.7/site-packages/stable_baselines3/common/monitor.py", line 79, in reset
    return self.env.reset(**kwargs)
  File "/media/lyc/files/U_omniverse/pkg/isaac_sim-2022.1.0/exts/omni.isaac.gym/omni/isaac/gym/vec_env/vec_env_base.py", line 130, in reset
    self._task.reset()
  File "/media/lyc/files/U_omniverse/pkg/isaac_sim-2022.1.0/cartpole_task.py", line 83, in reset
    self._cartpoles.set_joint_positions(dof_pos, indices=indices)
  File "/media/lyc/files/U_omniverse/pkg/isaac_sim-2022.1.0/exts/omni.isaac.core/omni/isaac/core/articulations/articulation_view.py", line 234, in set_joint_positions
    positions, device=self._device
IndexError: index 1 is out of bounds for dimension 0 with size 1
./python.sh: line 46: 19321 Segmentation fault      (core dumped) $python_exe "$@" $args
There was an error running python

Are there any examples for multiple environments training for Issac gym in Issac sim?I think the documentation for it is not detailed enough.
I used to use Isaac Gym package,while it can’t import usd.I think they should have different API.

HI @1324539608

Have you checked the https://docs.omniverse.nvidia.com/app_isaacsim/app_isaacsim/tutorial_gym_external_rl_examples.html?

Hi @1324539608

Please take a look at https://docs.omniverse.nvidia.com/app_isaacsim/app_isaacsim/tutorial_gym_external_rl_examples.html and GitHub - NVIDIA-Omniverse/OmniIsaacGymEnvs: Reinforcement Learning Environments for Omniverse Isaac Gym for documentation and examples of running multiple environments. The workflow is very similar to the Isaac Gym package.

Thanks,
Kelly