rofunc.learning.RofuncRL.tasks.isaacgymenv.ase.humanoid_strike

1.  Module Contents

1.1.  Classes

HumanoidStrikeTask

1.2.  Functions

compute_strike_observations
compute_strike_reward
compute_humanoid_reset

1.3.  API

class rofunc.learning.RofuncRL.tasks.isaacgymenv.ase.humanoid_strike.HumanoidStrikeTask(cfg, rl_device, sim_device, graphics_device_id, headless, virtual_screen_capture, force_render)

Bases: rofunc.learning.RofuncRL.tasks.isaacgymenv.ase.humanoid_amp_task.HumanoidAMPTask

get_task_obs_size()

pre_physics_step(actions)

rofunc.learning.RofuncRL.tasks.isaacgymenv.ase.humanoid_strike.compute_strike_observations(root_states: Tensor, tar_states: Tensor) → Tensor

rofunc.learning.RofuncRL.tasks.isaacgymenv.ase.humanoid_strike.compute_strike_reward(tar_pos: Tensor, tar_rot: Tensor, root_state: Tensor, prev_root_pos: Tensor, strike_body_vel: Tensor, dt: float, near_dist: float) → Tensor

rofunc.learning.RofuncRL.tasks.isaacgymenv.ase.humanoid_strike.compute_humanoid_reset(reset_buf: Tensor, progress_buf: Tensor, contact_buf: Tensor, contact_body_ids: Tensor, rigid_body_pos: Tensor, tar_contact_forces: Tensor, strike_body_ids: Tensor, max_episode_length: float, enable_early_termination: bool, termination_heights: Tensor) → Tuple[Tensor, Tensor]