h%.SrSSKJr SSKJr SSKrSSKrSSK J r J r J r SSK JrJrJrJr /SQrSSKJr "S S \R*\ \ \ 4\R,R.5r"S S \\ \ \ 4\R,R.5r"S S\\ \ \ 4\R,R.5r"SS\\ \ \ 4\R,R.5rg)aeA collection of wrappers that all use the LambdaAction class. * ``TransformAction`` - Transforms the actions based on a function * ``ClipAction`` - Clips the action within a bounds * ``DiscretizeAction`` - Discretizes a continuous Box action space into a single Discrete space * ``RescaleAction`` - Rescales the action within a minimum and maximum actions ) annotations)CallableN)ActTypeObsTypeWrapperActType)BoxDiscrete MultiDiscreteSpace)TransformAction ClipAction RescaleAction) rescale_boxc8\rSrSrSrSSjrSSjrSrg) r aApplies a function to the ``action`` before passing the modified value to the environment ``step`` function. A vector version of the wrapper exists :class:`gymnasium.wrappers.vector.TransformAction`. Example: >>> import numpy as np >>> import gymnasium as gym >>> env = gym.make("MountainCarContinuous-v0") >>> _ = env.reset(seed=123) >>> obs, *_= env.step(np.array([0.0, 1.0])) >>> obs array([-4.6397772e-01, -4.4808415e-04], dtype=float32) >>> env = gym.make("MountainCarContinuous-v0") >>> env = TransformAction(env, lambda a: 0.5 * a + 0.1, env.action_space) >>> _ = env.reset(seed=123) >>> obs, *_= env.step(np.array([0.0, 1.0])) >>> obs array([-4.6382770e-01, -2.9808417e-04], dtype=float32) Change logs: * v1.0.0 - Initially added c[RRRXUS9 [RRX5 UbX0lX lg)zInitialize TransformAction. Args: env: The environment to wrap func: Function to apply to the :meth:`step`'s ``action`` action_space: The updated action space of the wrapper given the function. )func action_spaceN)gymutilsRecordConstructorArgs__init__Wrapperrr)selfenvrrs ]/home/james-whalen/.local/lib/python3.13/site-packages/gymnasium/wrappers/transform_action.pyrTransformAction.__init__3sK ''00 , 1  T'  # ,  c$URU5$)zApply function to action.)r)ractions rr TransformAction.actionJsyy  r)rrN)rgym.Env[ObsType, ActType]rz#Callable[[WrapperActType], ActType]rzSpace[WrapperActType] | None)r rreturnr)__name__ __module__ __qualname____firstlineno____doc__rr __static_attributes__rrr r s-. &23 .!rr c"\rSrSrSrSSjrSrg)r OaClips the ``action`` pass to ``step`` to be within the environment's `action_space`. A vector version of the wrapper exists :class:`gymnasium.wrappers.vector.ClipAction`. Example: >>> import gymnasium as gym >>> from gymnasium.wrappers import ClipAction >>> import numpy as np >>> env = gym.make("Hopper-v4", disable_env_checker=True) >>> env = ClipAction(env) >>> env.action_space Box(-inf, inf, (3,), float32) >>> _ = env.reset(seed=42) >>> _ = env.step(np.array([5.0, -2.0, 0.0], dtype=np.float32)) ... # Executes the action np.array([1.0, -1.0, 0]) in the base environment Change logs: * v0.12.6 - Initially added * v1.0.0 - Action space is updated to infinite bounds as is technically correct c l^[TR[5(de[RR R U5 [R UTU4Sj[[R*[RTRRTRRS9S9 g)zjA wrapper for clipping continuous actions within the valid bound. Args: env: The environment to wrap c>[R"UTRRTRR5$N)npcliprlowhigh)r rs r%ClipAction.__init__..ss-((,,c.>.>.C.C!r)shapedtyperrrN) isinstancerrrrrrr r0infr6r7)rrs `rrClipAction.__init__gs #**C0000 ''006  &&,,&&,,  ! rr*N)rr"r$r%r&r'r(rr)r*rrr r Os * rr c.\rSrSrSrSSjrSrg)raDAffinely (linearly) rescales a ``Box`` action space of the environment to within the range of ``[min_action, max_action]``. The base environment :attr:`env` must have an action space of type :class:`spaces.Box`. If :attr:`min_action` or :attr:`max_action` are numpy arrays, the shape must match the shape of the environment's action space. A vector version of the wrapper exists :class:`gymnasium.wrappers.vector.RescaleAction`. Example: >>> import gymnasium as gym >>> from gymnasium.wrappers import RescaleAction >>> import numpy as np >>> env = gym.make("Hopper-v4", disable_env_checker=True) >>> _ = env.reset(seed=42) >>> obs, _, _, _, _ = env.step(np.array([1, 1, 1], dtype=np.float32)) >>> _ = env.reset(seed=42) >>> min_action = -0.5 >>> max_action = np.array([0.0, 0.5, 0.75], dtype=np.float32) >>> wrapped_env = RescaleAction(env, min_action=min_action, max_action=max_action) >>> wrapped_env_obs, _, _, _, _ = wrapped_env.step(max_action) >>> np.all(obs == wrapped_env_obs) np.True_ Change logs: * v0.15.4 - Initially added c[UR[5(de[RR R XUS9 [URX#5upEn[R UUUUS9 g)a>Constructor for the Rescale Action wrapper. Args: env (Env): The environment to wrap min_action (float, int or np.ndarray): The min values for each action. This may be a numpy array or a scalar. max_action (float, int or np.ndarray): The max values for each action. This may be a numpy array or a scalar. ) min_action max_actionr8N) r9rrrrrrrr )rrr@rA act_space_rs rrRescaleAction.__init__sw#**C0000 ''00 J 1 ))9)9:R d  " ! rr*N)rr"r@%np.floating | np.integer | np.ndarrayrArEr<r*rrrrs(4 & : :  rrcD\rSrSrSrS S SjjrSrSrSrSr g) DiscretizeActionaUniformly discretizes a continuous Box action space into a single Discrete space. Example 1 - Discretize Pendulum action space: >>> env = gym.make("Pendulum-v1") >>> env.action_space Box(-2.0, 2.0, (1,), float32) >>> obs, _ = env.reset(seed=42) >>> obs, *_ = env.step([-0.6]) >>> obs array([-0.17606162, 0.9843792 , 0.5292768 ], dtype=float32) >>> env = DiscretizeAction(env, bins=10) >>> env.action_space Discrete(10) >>> obs, _ = env.reset(seed=42) >>> obs, *_ = env.step(3) >>> obs array([-0.17606162, 0.9843792 , 0.5292768 ], dtype=float32) Example 2 - Discretize Reacher action space: >>> env = gym.make("Reacher-v5") >>> env.action_space Box(-1.0, 1.0, (2,), float32) >>> obs, _ = env.reset(seed=42) >>> obs, *_ = env.step([-0.3, -0.5]) >>> obs array([ 0.99908342, 0.99948506, 0.04280567, -0.03208766, 0.10445588, 0.11442572, -1.18958125, -1.97979484, 0.1054461 , -0.10896341]) >>> env = DiscretizeAction(env, bins=10) >>> env.action_space Discrete(100) >>> obs, _ = env.reset(seed=42) >>> obs, *_ = env.step(32) >>> obs array([ 0.99908342, 0.99948506, 0.04280567, -0.03208766, 0.10445588, 0.11442572, -1.18958118, -1.97979484, 0.1054461 , -0.10896341]) Example 2 - Discretize Reacher action space with MultiDiscrete: >>> env = gym.make("Reacher-v5") >>> env.action_space Box(-1.0, 1.0, (2,), float32) >>> obs, _ = env.reset(seed=42) >>> obs, *_ = env.step([-0.3, -0.5]) >>> obs array([ 0.99908342, 0.99948506, 0.04280567, -0.03208766, 0.10445588, 0.11442572, -1.18958125, -1.97979484, 0.1054461 , -0.10896341]) >>> env = DiscretizeAction(env, bins=10, multidiscrete=True) >>> env.action_space MultiDiscrete([10 10]) >>> obs, _ = env.reset(seed=42) >>> obs, *_ = env.step([3, 2]) >>> obs array([ 0.99908342, 0.99948506, 0.04280567, -0.03208766, 0.10445588, 0.11442572, -1.18958118, -1.97979484, 0.1054461 , -0.10896341]) c [UR[5(d [S5eURRUlURR UlURR SUl[R"[R"UR55(d9[R"[R"UR 55(a%[SURSUR 35eX0l [RRR!XS9 [R"R!X5 [U[$5(a*[R&"U/UR-5UlOT[+U5UR:Xd SURS[+U535e[R&"U5Ul[-UR5Vs/sHnS[R."URUUR UUR(US -5S S [R."URUUR UUR(US -5S S --PM snUlUR(aR(5Ulg [5[R6"UR(55Ulg s snf) zConstructor for the discretize action wrapper. Args: env: The environment to wrap. bins: int or tuple of ints (number of bins per dimension). multidiscrete: If True, use MultiDiscrete action space instead of flattening to Discrete. z@DiscretizeAction is only compatible with Box continuous actions.rz>Discretization requires action space to be finite. Found: low=z, high=)binsz,bins must match action dimensions: expected z, got g?N)r9rr TypeErrorr2r3r6n_dimsr0anyisinf ValueError multidiscreterrrr ActionWrapperintarrayrJlenrangelinspace bin_centersr r prod)rrrJrRis rrDiscretizeAction.__init__sL#**C00R ##''$$)) hhnnQ' 66"((488$ % %0C)D)D"hhZwtyyk;  + ''000A ""4- dC $$++!56DID T[[( ]=dkk]&QTUYQZP[\ ](DI4;;'  (  DHHQK1tyy|a7GH"M++dhhqk499Q<19IJ12NO  (      -dii 8D  (); '     88G3/ /''; ; sAB*c/n[UR5HnURX-5 X-nM [[U55$r/)reversedrJappendlist)r flat_indexrebs rr`!DiscretizeAction._unflatten_index@sB$))$A NN:> *  J%HW%&&r)rrYrJr3r2rRrNN)F)rr"rJzint | tuple[int, ...]rRbool) r$r%r&r'r(rr rmr`r)r*rrrGrGs?5v$ 4= &4=$4= 4=l D <'rrG)r( __future__rcollections.abcrnumpyr0 gymnasiumrgymnasium.corerrrgymnasium.spacesrr r r __all__gymnasium.wrappers.utilsrrSrrr r rrGr*rrrs#$;;@@ =03!g~w679X9X3!l- G^W45syy7V7V- `6 G^W45syy7V7V6 rM'G^W45II##M'r