Skip to content

Humanoid

Lerax port of Gymnasium's Humanoid environment. A 3D humanoid with 17 actuated joints must walk in the +x direction while remaining upright.

Observation space

Flattened concatenation of qpos, qvel, cinert[1:], cvel[1:], qfrc_actuator[6:], and cfrc_ext[1:]. Each of the last four blocks is individually switchable via include_*_in_observation (all default True). When exclude_current_positions_from_observation=True (default) the first two entries of qpos are dropped. Unbounded Box.

Action space

Box(low, high) from the model's actuator_ctrlrange — 17 continuous joint torques.

Reward

forward_reward + healthy_reward - ctrl_cost - contact_cost with

  • forward_reward = forward_reward_weight * x_velocity_of_center_of_mass (default weight 1.25)
  • healthy_reward = is_healthy * healthy_reward (default 5.0)
  • ctrl_cost = ctrl_cost_weight * sum(action ** 2) (default 0.1)
  • contact_cost = contact_cost_weight * clip(sum(cfrc_ext ** 2), -inf, 10.0) (default weight 5e-7)

Termination

If terminate_when_unhealthy=True (default), terminates when torso z leaves healthy_z_range=(1.0, 2.0). No built-in truncation.

lerax.env.mujoco.Humanoid

Bases: AbstractMujocoEnv[Float[Array, '...'], Float[Array, '...']]

MJX-based humanoid environment roughly matching Gymnasium's Humanoid-v5.

unwrapped property 

unwrapped: Self

Return the unwrapped environment

action_mask 

action_mask(
    state: MujocoEnvState, *, key: Key[Array, ""]
) -> None

transition 

transition(
    state: MujocoEnvState,
    action: ActType,
    *,
    key: Key[Array, ""],
) -> MujocoEnvState

truncate 

truncate(state: MujocoEnvState) -> Bool[Array, '']

default_renderer 

default_renderer() -> MujocoRenderer

render 

render(state: MujocoEnvState, renderer: AbstractRenderer)

render_states 

render_states(
    states: Sequence[StateType],
    renderer: AbstractRenderer | Literal["auto"] = "auto",
    dt: float = 0.0,
)

Render a sequence of frames from multiple states.

Parameters:

Name Type Description Default
states Sequence[StateType]

A sequence of environment states to render.

 required
renderer AbstractRenderer | Literal['auto']

The renderer to use for rendering. If "auto", uses the default renderer.

 'auto'
dt float

The time delay between rendering each frame, in seconds.

 0.0

render_stacked 

render_stacked(
    states: StateType,
    renderer: AbstractRenderer | Literal["auto"] = "auto",
    dt: float = 0.0,
)

Render multiple frames from stacked states.

Stacked states are typically batched states stored in a pytree structure.

Parameters:

Name Type Description Default
states StateType

A pytree of stacked environment states to render.

 required
renderer AbstractRenderer | Literal['auto']

The renderer to use for rendering. If "auto", uses the default renderer.

 'auto'
dt float

The time delay between rendering each frame, in seconds.

 0.0

reset 

reset(
    *, key: Key[Array, ""]
) -> tuple[StateType, ObsType, dict]

Wrap the functional logic into a Gym API reset method.

Parameters:

Name Type Description Default
key Key[Array, '']

A JAX PRNG key for any stochasticity in the reset.

 required

Returns:

Type Description
tuple[StateType, ObsType, dict]

A tuple of the initial state, initial observation, and additional info.

step 

step(
    state: StateType,
    action: ActType,
    *,
    key: Key[Array, ""],
) -> tuple[
    StateType,
    ObsType,
    Float[Array, ""],
    Bool[Array, ""],
    Bool[Array, ""],
    dict,
]

Wrap the functional logic into a Gym API step method.

Parameters:

Name Type Description Default
state StateType

The current environment state.

 required
action ActType

The action to take.

 required
key Key[Array, '']

A JAX PRNG key for any stochasticity in the step.

 required

Returns:

Type Description
tuple[StateType, ObsType, Float[Array, ''], Bool[Array, ''], Bool[Array, ''], dict]

A tuple of the next state, observation, reward, terminal flag, truncate flag, and additional info.

model_from_path staticmethod 

model_from_path(xml_file: str | Path) -> mujoco.MjModel