parameters: actions: (n_samples, action_dim) outputs: obs: (n_samples, obs_dim) rewards: (n_samples,)

Reset all robots

Reset some environments. Calls self._reset_dofs(env_ids), self._reset_root_states(env_ids), and self._resample_commands(env_ids)

Calculate the expectation value of I_i(φ). Parameters: phi (float): The given phase time. offset (float): The offset

Random pushes the robots. Emulates an impulse by setting a randomized base velocity.

Get rotation from transform

Resets DOF position and velocities of selected environmments Positions are randomly selected within 0.5:1.5 x default positions. Velo

Resets ROOT states position and velocities of selected environmments if target_root_states is not None, reset to target_root_states

Pre-process the config for PPO training

Construct 3D identity rotation given shape

Construct 3D rotation from quaternion (the quaternion needs not to be normalized).

Get translation from transform

model: The original PyTorch model. input_keys: List of input names as keys for the input dictionary.

Check if environments need to be reset

Computes observations

Compute the returns and advantages for the given policy state. This function calculates the returns and advantages for each step in the

Compute the returns and advantages for the given policy state. This function calculates the returns and advantages for each step in the

Compute rewards Calls each reward function which had a non-zero scale (processed in self._prepare_reward_function()) adds eac

Compute torques from actions. Actions can be interpreted as position or velocity targets given to a PD controller, or directly as scaled

Compute torques from actions. Actions can be interpreted as position or velocity targets given to a PD controller, or directly as scaled

Creates environments: 1. loads the robot URDF/MJCF asset, 2. For each environment 2.1 creates the environme

Adds a ground plane to the simulation, sets friction and restitution based on the cfg.

Adds a heightfield terrain to the simulation, sets parameters based on the cfg.

Adds a triangle mesh terrain to the simulation, sets parameters based on the cfg.

Draws visualizations for dubugging (slows down simulation a lot). Default behaviour: draws height measurement points