h*SrSSKJr SSKJr SSKJr SSKJr SSK r SSK J r SSK JrJr SS KJr SS KJrJr SS KJrJrJrJr SS KJr "S S\5r"SS\5r"SS\5r"SS\5rg)z3Vectorizes action wrappers to work for `VectorEnv`.) annotations)Callable)deepcopy)AnyN)Space)ActTypeEnv)warn)VectorActionWrapper VectorEnv) batch_space concatenatecreate_empty_arrayiterate)transform_actioncP^\rSrSrSrSSU4SjjjrSSjrSrU=r$) TransformActionajTransforms an action via a function provided to the wrapper. The function :attr:`func` will be applied to all vector actions. If the observations from :attr:`func` are outside the bounds of the ``env``'s action space, provide an :attr:`action_space` which specifies the action space for the vectorized environment. Example - Without action transformation: >>> import gymnasium as gym >>> envs = gym.make_vec("MountainCarContinuous-v0", num_envs=3) >>> _ = envs.action_space.seed(123) >>> obs, info = envs.reset(seed=123) >>> for _ in range(10): ... obs, rew, term, trunc, info = envs.step(envs.action_space.sample()) ... >>> envs.close() >>> obs array([[-0.46553135, -0.00142543], [-0.498371 , -0.00715587], [-0.46515748, -0.00624371]], dtype=float32) Example - With action transformation: >>> import gymnasium as gym >>> from gymnasium.spaces import Box >>> def shrink_action(act): ... return act * 0.3 ... >>> envs = gym.make_vec("MountainCarContinuous-v0", num_envs=3) >>> new_action_space = Box(low=shrink_action(envs.action_space.low), high=shrink_action(envs.action_space.high)) >>> envs = TransformAction(env=envs, func=shrink_action, action_space=new_action_space) >>> _ = envs.action_space.seed(123) >>> obs, info = envs.reset(seed=123) >>> for _ in range(10): ... obs, rew, term, trunc, info = envs.step(envs.action_space.sample()) ... >>> envs.close() >>> obs array([[-0.48468155, -0.00372536], [-0.47599354, -0.00545912], [-0.46543318, -0.00615723]], dtype=float32) c p>[TU]U5 Uc$Ub X@l[X@R5UlOX0lUbX@lUR [URUR5:wa<[ SUSUR S[URUR535 X lg)anConstructor for the lambda action wrapper. Args: env: The vector environment to wrap func: A function that will transform an action. If this transformed action is outside the action space of ``env.action_space`` then provide an ``action_space``. action_space: The action spaces of the wrapper. If None, then it is computed from ``single_action_space``. If ``single_action_space`` is not provided either, then it is assumed to be the same as ``env.action_space``. single_action_space: The action space of the non-vectorized environment. If None, then it is assumed the same as ``env.single_action_space``. NzFor z], the action space and the batched single action space don't match as expected, action_space=z, batched single_action_space=)super__init__single_action_spacer num_envs action_spacer func)selfenvrrr __class__s d/home/james-whalen/.local/lib/python3.13/site-packages/gymnasium/wrappers/vector/vectorize_action.pyrTransformAction.__init__=s   ".+>($/0C]]$S! , ".+>(    D,D,Ddmm T T sexy|zJzJyKKijuvzvNvNPTP]P]j^i_`  c$URU5$)z(Applies the :attr:`func` to the actions.)rractionss rr$TransformAction.actions^syy!!r!)rrr)NN)rr rzCallable[[ActType], Any]r Space | Nonerr&r$rreturnr) __name__ __module__ __qualname____firstlineno____doc__rr$__static_attributes__ __classcell__rs@rrrsL'Z&*,0  '#  * B""r!rc\^\rSrSrSr"SS\5rSU4SjjrS SjrSr U=r $) VectorizeTransformActioncaVectorizes a single-agent transform action wrapper for vector environments. Example - Without action transformation: >>> import gymnasium as gym >>> envs = gym.make_vec("MountainCarContinuous-v0", num_envs=3) >>> _ = envs.action_space.seed(123) >>> obs, info = envs.reset(seed=123) >>> obs, rew, term, trunc, info = envs.step(envs.action_space.sample()) >>> envs.close() >>> obs array([[-4.6343064e-01, 9.8971417e-05], [-4.4488689e-01, -1.9375233e-03], [-4.3118435e-01, -1.5342437e-03]], dtype=float32) Example - Adding a transform that applies a ReLU to the action: >>> import gymnasium as gym >>> from gymnasium.wrappers import TransformAction >>> envs = gym.make_vec("MountainCarContinuous-v0", num_envs=3) >>> envs = VectorizeTransformAction(envs, wrapper=TransformAction, func=lambda x: (x > 0.0) * x, action_space=envs.single_action_space) >>> _ = envs.action_space.seed(123) >>> obs, info = envs.reset(seed=123) >>> obs, rew, term, trunc, info = envs.step(envs.action_space.sample()) >>> envs.close() >>> obs array([[-4.6343064e-01, 9.8971417e-05], [-4.4354835e-01, -5.9898634e-04], [-4.3034542e-01, -6.9532328e-04]], dtype=float32) c"\rSrSrSrSSjrSrg)#VectorizeTransformAction._SingleEnvz@Fake single-agent environment used for the single-agent wrapper.cXlg)z%Constructor for the fake environment.Nr)rrs rr,VectorizeTransformAction._SingleEnv.__init__s , r!r8N)rr)r)r*r+r,r-rr.r!r _SingleEnvr5s N -r!r;c >[TU]U5 U"URURR540UD6UlUR R Ul[URUR5UlUR URR :HUl [URRUR5Ul g)zConstructor for the vectorized lambda action wrapper. Args: env: The vector environment to wrap wrapper: The wrapper to vectorize **kwargs: Arguments for the LambdaAction wrapper N) rrr;rrwrapperrr rsame_outrout)rrr=kwargsrs rr!VectorizeTransformAction.__init__s ttxx/K/KLWPVW #'<<#<#< '(@(@$--P))TXX-B-BB %dhh&B&BDMMRr!c l^TR(aH[TRR[ U4Sj[ TR U555U5$[[TRR[ U4Sj[ TR U555TR55$)zApplies the wrapper to each of the action. Args: actions: The actions to apply the function to Returns: The updated actions using the wrapper func c3Z># UH nTRRU5v M" g7fNr=r.0actionrs r 3VectorizeTransformAction.actions..s*"ELL%%f--"E(+c3Z># UH nTRRU5v M" g7frDrErFs rrIrJs*&IF ))&11&IrK) r>rrrtuplerrrr?r#s` rr$ VectorizeTransformAction.actionss ==,,")$*;*;W"E  HH00&-d.?.?&IHH   r!)rr?r>rr=)rr r=z&type[transform_action.TransformAction]r@rr') r)r*r+r,r-r r;rr$r.r/r0s@rr2r2csC:-S-S S8S S,r!r2c0^\rSrSrSrSU4SjjrSrU=r$) ClipActionaClip the continuous action within the valid :class:`Box` observation space bound. Example - Passing an out-of-bounds action to the environment to be clipped. >>> import numpy as np >>> import gymnasium as gym >>> envs = gym.make_vec("MountainCarContinuous-v0", num_envs=3) >>> envs = ClipAction(envs) >>> _ = envs.action_space.seed(123) >>> obs, info = envs.reset(seed=123) >>> obs, rew, term, trunc, info = envs.step(np.array([5.0, -5.0, 2.0])) >>> envs.close() >>> obs array([[-0.4624777 , 0.00105192], [-0.44504836, -0.00209899], [-0.42884544, 0.00080468]], dtype=float32) cB>[TU]U[R5 g)zXConstructor for the Clip Action wrapper. Args: env: The vector environment to wrap N)rrrrP)rrrs rrClipAction.__init__s .99:r!r:)rr r)r*r+r,r-rr.r/r0s@rrPrPs";;r!rPc<^\rSrSrSrSU4SjjrSrU=r$) RescaleActionaAffinely rescales the continuous action space of the environment to the range [min_action, max_action]. Example - Without action scaling: >>> import numpy as np >>> import gymnasium as gym >>> envs = gym.make_vec("MountainCarContinuous-v0", num_envs=3) >>> _ = envs.action_space.seed(123) >>> obs, info = envs.reset(seed=123) >>> for _ in range(10): ... obs, rew, term, trunc, info = envs.step(0.5 * np.ones((3, 1))) ... >>> envs.close() >>> obs array([[-0.44799727, 0.00266526], [-0.4351738 , 0.00133522], [-0.42683297, 0.00048403]], dtype=float32) Example - With action scaling: >>> import numpy as np >>> import gymnasium as gym >>> envs = gym.make_vec("MountainCarContinuous-v0", num_envs=3) >>> envs = RescaleAction(envs, 0.0, 1.0) >>> _ = envs.action_space.seed(123) >>> obs, info = envs.reset(seed=123) >>> for _ in range(10): ... obs, rew, term, trunc, info = envs.step(0.5 * np.ones((3, 1))) ... >>> envs.close() >>> obs array([[-0.48657528, -0.00395268], [-0.47377947, -0.00529102], [-0.46546045, -0.00614867]], dtype=float32) cB>[TU]U[RUUS9 g)aIInitializes the :class:`RescaleAction` wrapper. Args: env (Env): The vector 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_actionN)rrrrV)rrrYrZrs rrRescaleAction.__init__s)    * *!!  r!r:)rr rYfloat | int | np.ndarrayrZr\rTr0s@rrVrVs/ D  - -   r!rV) r- __future__rcollections.abcrcopyrtypingrnumpynp gymnasiumrgymnasium.corerr gymnasium.loggerr gymnasium.vectorr r gymnasium.vector.utilsr rrrgymnasium.wrappersrrr2rPrVr:r!rrisf9"$'!;XX/M")M"`W2Wt;);65 ,5 r!