Skip to content

Transform Action

lerax.wrapper.TransformAction

Bases: AbstractPureTransformActionWrapper[WrapperActType, WrapperMaskType, StateType, ActType, ObsType, MaskType]

Apply a function to the action before passing it to the environment.

Attributes:

Name Type Description
env AbstractEnvLike[StateType, ActType, ObsType, MaskType]

The environment to wrap.
func Callable[[WrapperActType], ActType]

The function to apply to the action.
action_space AbstractSpace[WrapperActType, WrapperMaskType]

The action space of the wrapper.

Parameters:

Name Type Description Default
env AbstractEnvLike[StateType, ActType, ObsType, MaskType]

The environment to wrap.

 required
func Callable[[WrapperActType], ActType]

The function to apply to the action.

 required
action_space AbstractSpace[WrapperActType, WrapperMaskType]

The action space of the wrapper.

 required

name property 

name: str

Return the name of the environment

observation_space property 

observation_space: AbstractSpace[ObsType, Any]

unwrapped property 

unwrapped: AbstractEnv

Return the wrapped environment

env instance-attribute 

env: AbstractEnvLike[
    StateType, ActType, ObsType, MaskType
] = env

func instance-attribute 

func: Callable[[WrapperActType], ActType] = func

mask_func instance-attribute 

mask_func: Callable[[MaskType], WrapperMaskType] = mask_func

action_space instance-attribute 

action_space: AbstractSpace[
    WrapperActType, WrapperMaskType
] = action_space

initial 

initial(
    *, key: Key[Array, ""]
) -> TransformActionState[StateType]

action_mask 

action_mask(
    state: TransformActionState[StateType],
    *,
    key: Key[Array, ""],
) -> WrapperMaskType | None

transition 

transition(
    state: TransformActionState[StateType],
    action: WrapperActType,
    *,
    key: Key[Array, ""],
) -> TransformActionState[StateType]

observation 

observation(
    state: TransformActionState[StateType],
    *,
    key: Key[Array, ""],
) -> ObsType

reward 

reward(
    state: TransformActionState[StateType],
    action: WrapperActType,
    next_state: TransformActionState[StateType],
    *,
    key: Key[Array, ""],
) -> Float[Array, ""]

terminal 

terminal(
    state: TransformActionState[StateType],
    *,
    key: Key[Array, ""],
) -> Bool[Array, ""]

truncate 

truncate(
    state: TransformActionState[StateType],
) -> Bool[Array, ""]

state_info 

state_info(state: TransformActionState[StateType]) -> dict

transition_info 

transition_info(
    state: TransformActionState[StateType],
    action: WrapperActType,
    next_state: TransformActionState[StateType],
) -> dict

default_renderer 

default_renderer() -> AbstractRenderer

Return the default renderer for the wrapped environment

render 

render(state: WrapperStateType, renderer: AbstractRenderer)

Render a frame from a state

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.

__init__ 

__init__(
    env: AbstractEnvLike[
        StateType, ActType, ObsType, MaskType
    ],
    func: Callable[[WrapperActType], ActType],
    action_space: AbstractSpace[
        WrapperActType, WrapperMaskType
    ],
    mask_func: Callable[
        [MaskType], WrapperMaskType
    ] = lambda x: x,
)