h' SrSSKJr SSKrSSKJrJr SSKrSSKJ r SSK r SSK J r "SS\ \\\S 4\45rg) zBImplementation of a space that represents finite-length sequences.) annotationsN)AnyUnion)NDArray)Spacec^\rSrSrSrSSU4SjjjrSSU4Sjjjr\S5rSSSjjr SSjr SSjr SS jr SS jr SS jrSS jrS rU=r$)SequenceaThis space represent sets of finite-length sequences. This space represents the set of tuples of the form :math:`(a_0, \dots, a_n)` where the :math:`a_i` belong to some space that is specified during initialization and the integer :math:`n` is not fixed Example: >>> from gymnasium.spaces import Sequence, Box >>> observation_space = Sequence(Box(0, 1), seed=0) >>> observation_space.sample() (array([0.6822636], dtype=float32), array([0.18933342], dtype=float32), array([0.19049619], dtype=float32)) >>> observation_space.sample() (array([0.83506], dtype=float32), array([0.9053838], dtype=float32), array([0.5836242], dtype=float32), array([0.63214064], dtype=float32)) Example with stacked observations >>> observation_space = Sequence(Box(0, 1), stack=True, seed=0) >>> observation_space.sample() array([[0.6822636 ], [0.18933342], [0.19049619]], dtype=float32) c$>[U[5(dS[U535eXlX0lUR(a9[ R RRURS5Ul [TU]-SSU5 g)a3Constructor of the :class:`Sequence` space. Args: space: Elements in the sequences this space represent must belong to this space. seed: Optionally, you can use this argument to seed the RNG that is used to sample from the space. stack: If ``True`` then the resulting samples would be stacked. zFExpects the feature space to be instance of a gym Space, actual type: N) isinstancertype feature_spacestackgymvectorutils batch_spacestacked_feature_spacesuper__init__)selfspaceseedr __class__s S/home/james-whalen/.local/lib/python3.13/site-packages/gymnasium/spaces/sequence.pyrSequence.__init__%s 5   b STXY^T_S` a b # ::03 0@0@0L0L""A1D & tT*c>Uc*[TU]S5URRS54$[U[5(a[TU]U5n[ UR R [R"[R5R55n[TU]U5 X RRU54$[U[[45(aV[U5S:wa[S[U535e[TU]US5URRUS54$[S[!U535e)a=Seed the PRNG of the Sequence space and the feature space. Depending on the type of seed, the subspaces will be seeded differently * ``None`` - All the subspaces will use a random initial seed * ``Int`` - The integer is used to seed the :class:`Sequence` space that is used to generate a seed value for the feature space. * ``Tuple of ints`` - A tuple for the :class:`Sequence` and feature space. Args: seed: An optional int or tuple of ints to seed the PRNG. See above for more details Returns: A tuple of the seeding values for the Sequence and feature space NzYExpects the seed to have two elements for the Sequence and feature space, actual length: rr z0Expected None, int, tuple of ints, actual type: )rrrr int np_randomintegersnpiinfoint32maxtuplelistlen ValueError TypeErrorr)rr super_seed feature_seedrs rr Sequence.seed?s! <7<%t'9'9'>'>t'DD D c " "d+Jt~~66rxx7I7M7MNOL GL 1166|DD D udm , ,4yA~ opstxpyoz{7<Q($*<*<*A*A$q'*JJ JB4:,O rcg)zDChecks whether this space can be flattened to a :class:`spaces.Box`.Frs ris_np_flattenableSequence.is_np_flattenableasrc^^^TbTb[STST35eTb5TRTSS5n[UU4Sj[U555nOqTb5TRTSS5n[UU4Sj[U555nO9TRR S5n[U4S j[U555nTR (aq[RRRTR[U55n[RRRTRXE5$U$) aGenerates a single random sample from this space. Args: mask: An optional mask for (optionally) the length of the sequence and (optionally) the values in the sequence. If you specify ``mask``, it is expected to be a tuple of the form ``(length_mask, sample_mask)`` where ``length_mask`` is * ``None`` - The length will be randomly drawn from a geometric distribution * ``int`` - Fixed length * ``np.ndarray`` of integers - Length of the sampled sequence is randomly drawn from this array. The second element of the tuple ``sample_mask`` specifies how the feature space will be sampled. Depending on if mask or probability is used will affect what argument is used. probability: See mask description above, the only difference is on the ``sample_mask`` for the feature space being probability rather than mask. Returns: A tuple of random length with random samples of elements from the :attr:`feature_space`. zIOnly one of `mask` or `probability` can be provided, actual values: mask=z, probability=rmaskc3\># UH!nTRRTSS9v M# g7f)r )r6Nrsample).0_r6rs r "Sequence.sample..s-#AUA""))tAw)7AU), probabilityc3\># UH!nTRRTSS9v M# g7f)r )r?Nr8)r:r;r?rs rr<r=s0#-A""))k!n)E-r>?c3X># UHnTRR5v M! g7fNr8)r:r;rs rr<r=s'#5I""))++5Is'*)r+generate_sample_lengthr(ranger" geometricrrrrcreate_empty_arrayrr* concatenate)rr6r? sample_lengthsampled_valuesouts``` rr9Sequence.samplefs7@   7[\`[aaop{o|}   77QHM"#AF}AU#N $ 77 A VM"#}-#N !NN44T:M"#5:=5I#N ::**""55""C$7C::##//0B0BNX XrcUGbB[R"[U5[R5(aSU::d SUSU35eU$[ U[R 5(a[ UR5S:XdSUSUR35e[R"SU:*5(d SUSU35e[R"UR[R5(dS US UR35eURRU5$[S US [U535eURRS 5$)zAGenerate the sample length for a given length mask and mask type.rzExpects the length mask of `z5` to be greater than or equal to zero, actual value: r z)Expects the shape of the length mask of `z%` to be 1-dimensional, actual shape: z*Expects all values in the length_mask of `z6` to be greater than or equal to zero, actual values: z"Expects the length mask array of `z,` to have dtype of np.integer, actual type: z$Expects the type of length_mask of `z1` to be an integer or a np.ndarray, actual type: rA)r$ issubdtyperintegerr ndarrayr*shapealldtyper"choicer,rF)r length_mask mask_types rrDSequence.generate_sample_lengths  "}}T+. ;;$@1)ykInozpApAoBCC/vv$O? {KABMANOO}}%%rzzC7 {BnozpApAoBCC~~,,[99:9+Evw{}HxIwJK >>++D1 1rc ^TR(aG[U4Sj[RRR TR U555$[U[5=(a [U4SjU55$)z?Return boolean specifying if x is a valid member of this space.c3B># UHnUTR;v M g7frC)rr:itemrs rr<$Sequence.contains..s#SD***Ssc3Z># UH nTRRU5v M" g7frC)rcontainsrZs rr<r\s(0>?d""++D11as(+) rrRrrriteraterr r()rxs` rr^Sequence.containssn ::JJ,,44T5O5OQRS  a'C0>?0- rc<SURSURS3$)z,Gives a string representation of this space.z Sequence(z, stack=))rrr2s r__repr__Sequence.__repr__s"4--.htzzl!DDrcUR(aURRU5$UVs/sHo RRU5PM sn$s snf)zCConvert a batch of samples from this space to a JSONable data type.)rr to_jsonablerrsample_nr9s rrgSequence.to_jsonablesI ::--99(C CIQRv&&226:R RRs$AcUR(aURRU5$UVs/sH'n[URRU55PM) sn$s snf)zCConvert a JSONable data type to a batch of samples from this space.)rr from_jsonabler(rrhs rrlSequence.from_jsonables[ ::--;;HE EOWNVFd((66v>?h s.A"c[U[5=(a9 URUR:H=(a URUR:H$)z7Check whether ``other`` is equivalent to this instance.)r r rr)rothers r__eq__Sequence.__eq__sA uh ' *""e&9&99 * ekk) r)rrr)NF)rz Space[Any]rz int | np.random.Generator | NonerboolrC)rzint | tuple[int, int] | Nonereturnztuple[int, int])NN)r63None | tuple[None | int | NDArray[np.integer], Any]r?rtrsztuple[Any] | Any)rUz'None | np.integer | NDArray[np.integer]rVz None | strrsr!)r`rrsrr)rsstr)riz&typing.Sequence[tuple[Any, ...] | Any]rslist[list[Any]])rirvrszlist[tuple[Any, ...] | Any])rorrsrr)__name__ __module__ __qualname____firstlineno____doc__rrpropertyr3r9rDr^rdrgrlrp__static_attributes__ __classcell__)rs@rr r s026 ++/+ ++4  D  < < < <|2<22 2B ES>S S  rr .)r{ __future__rtypingrrnumpyr$ numpy.typingr gymnasiumrgymnasium.spaces.spacerr(r r1rrrsBH"  (_ uU5c?C/01_ r