nim?ZSrSSKJr SSKJr SSKJr SSKrSSKrSSKrSSKrSSK r SSK r SSK r SSK r SSKJs Jr "SS\5r"SS \5r"S S \5r"S S \5r"SS\5r"SS\5r"SS\5r"SS\5r"SS\5r"SS\5rg)z%Wrappers for OpenAI Gym environments.)absolute_import)division)print_functionNc0\rSrSrSrSrSrSrSrSr g) AutoReset z9Automatically reset environment when the episode is done.cXlSUlg)NT)_env_doneselfenvs f/home/james-whalen/.local/lib/python3.13/site-packages/pybullet_envs/minitaur/agents/tools/wrappers.py__init__AutoReset.__init__#IDJc.[URU5$Ngetattrr r names r __getattr__AutoReset.__getattr__' 499d ##rcUR(a"URR5SS04up#pEOURRU5up#pEX@lX#XE4$)NgF)r r resetstepr actionobservrewarddoneinfos rrAutoReset.step*sP zz#'99??#4c5"#D fdD#'99>>  fdJ 4 %%rcDSUlURR5$)NF)r r rr s rrAutoReset.reset2sDJ 99?? r)r r N __name__ __module__ __qualname____firstlineno____doc__rrrr__static_attributes__rrrr sA$&rrc*\rSrSrSrSrSrSrSrg) ActionRepeat7z'Repeat the agent action multiple steps.cXlX lgr)r _amount)r ramounts rrActionRepeat.__init__:s ILrc.[URU5$rrrs rrActionRepeat.__getattr__>rrcSnSnSnX@R:aFU(d?URRU5upVp'X6- nUS- nX@R:a U(dM?WX2W4$)NFr)r6r r)r r!r$ total_reward current_stepr"r#r%s rrActionRepeat.stepAse DLL  %d#'99>>  fdlal  %dd ># $$rcURRU5up#pEU=RS- slX RURUR-'UR 5nX#XE4$)Nr<)r rr_r`rb_select_framesr s rrFrameHistory.stepsX!%!7FDJJ!OJ06LLdnn,-  "F 4 %%rcURR5n[R"USURS5UlSUlUR5$)Nrjr)r rrKrqrbr`r_r{r r"s rrFrameHistory.resetsE YY__ F99VI.BDLDJ     rcURVs/sHoRU- UR-PM nnURUnUR(a'[ R "USURSS-5nU$s snf)Nrkrm)r^r_rbr`rcrKrsrt)r indexindicesr"s rr{FrameHistory._select_framessnBFBTBTUBT U"dnn4BTGU \\' "F }}zz&%&,,qr*:":;f M Vs%A?)r`rbr rcr^r_N) r+r,r-r.r/rrpropertyrnrrr{r0r1rrrZrZbs27.$ % %&! rrZc@\rSrSrSrSrSr\S5rSr Sr Sr g ) FrameDeltazFConvert the observation to a difference from the previous observation.cXlSUlgrr _lastr s rrFrameDelta.__init__rrc.[URU5$rrrs rrFrameDelta.__getattr__rrcURRRnURRRnX- X!- p![R R X5$r)r rnrorprurvrwrxs rrnFrameDelta.observation_spacesJ )) % % ) )C 99 & & + +D DJ ::>># $$rcnURRU5up#pEX R- nX lXcXE4$r)r rr)r r!r"r#r$r%deltas rrFrameDelta.steps5!%!7FD ZZ EJ $ $$rcFURR5nXlU$r)r rrr~s rrFrameDelta.resets YY__ FJ MrrN) r+r,r-r.r/rrrrnrrr0r1rrrrs-N$ % % % rrcf\rSrSrSrSSjrSr\S5r\S5r Sr S r S r S r S rS rg)RangeNormalizezCNormalize the specialized observation and action ranges to [-1, 1].Nc8XlUSL=(a% URURR5UlUSLaUR(d [ S5eUc0UR(d[ R RS5 USL=(a% URURR5Ul USLaUR(d [ S5eUc2UR(d [ R RS5 ggg)NFTz,Cannot normalize infinite observation range.z+Not normalizing infinite observation range.z'Cannot normalize infinite action range.z&Not normalizing infinite action range.) r _is_finitern_should_normalize_observ ValueErrorrQrRr%rO_should_normalize_action)r rr"r!s rrRangeNormalize.__init__sI%+5%8&R%)__TYY5P5P%Q ! ~d;; E FF ~d;;jjooCD%+5%8&M%)__TYY5K5K%L ! ~d;; @ AA ~d;;jjoo>?<~rc.[URU5$rrrs rrRangeNormalize.__getattr__rrcURRnUR(dU$[RR [ R"UR5*[ R"UR55$r) r rnrrurvrwrKonesrtr spaces rrn RangeNormalize.observation_spacesQ II ' 'E  ( ( l ::>>2775;;//1E FFrcURRnUR(dU$[RR [ R"UR5*[ R"UR55$r) r rOrrurvrwrKrrtrs rrORangeNormalize.action_spacesQ II " "E  ( ( l ::>>2775;;//1E FFrcUR(aURU5nURRU5up#pEUR(aUR U5nX#XE4$r)r_denormalize_actionr rr_normalize_observr s rrRangeNormalize.stepsV $$''/f!%!7FD $$%%f-f 4 %%rc~URR5nUR(aURU5nU$r)r rrrr~s rrRangeNormalize.resets0 YY__ F $$%%f-f MrcURRRnURRRnUS-S- X2- -U-nU$)Nr<rm)r rOrorp)r r!min_max_s rr"RangeNormalize._denormalize_actionsK 99 ! ! % %D 99 ! ! & &DqjA  - 4F MrcURRRnURRRnSX- -X2- - S- nU$)Nrmr<)r rnrorp)r r"rrs rr RangeNormalize._normalize_observsI 99 & & * *D 99 & & + +D &- DK 01 4F Mrc[R"UR5R5=(a. [R"UR5R5$r)rKisfiniteroallrprs rrRangeNormalize._is_finites9 ;;uyy ! % % ' IBKK ,C,G,G,IIr)r rr)NN)r+r,r-r.r/rrrrnrOrrrrrr0r1rrrrsVK @$ G G  G G &   Jrrc:\rSrSrSrSrSr\S5rSr Sr g) ClipActionzAClip out of range actions to the action space of the environment.cXlgrr r s rrClipAction.__init__sIrc.[URU5$rrrs rrClipAction.__getattr__rrcURRRn[RR [ R*[ R"U5-[ R[ R"U5-5$r) r rOrtrurvrwrKinfr)r rts rrOClipAction.action_spacesP II " " ( (E ::>>266'BGGEN2BFFRWWU^4K LLrcURRn[R"XRUR 5nURR U5$r)r rOrKcliprorpr)r r!rOs rrClipAction.step s@99))L WWV--|/@/@ AF 99>>& !!rrN) r+r,r-r.r/rrrrOrr0r1rrrrs*I$ M M"rrc0\rSrSrSrSrSrSrSrSr g) LimitDurationiz-End episodes after specified number of steps.c*XlX lSUlgr)r _durationr_)r rdurations rrLimitDuration.__init__sINDJrc.[URU5$rrrs rrLimitDuration.__getattr__rrcURc [S5eURRU5up#pEU=RS- slURUR:a SnSUlX#XE4$)NzMust reset environment.r<T)r_ RuntimeErrorr rrr s rrLimitDuration.stepsc zz 2 33!%!7FDJJ!OJ zzT^^# ddj 4 %%rcDSUlURR5$)Nr)r_r rr(s rrLimitDuration.reset&sDJ 99?? r)rr r_Nr*r1rrrrs5 $&rrc\rSrSrSrSrSrSrSrSr Sr S r S r S r \S 5r\S 5rSrSSjrSSjrSrSrSrSrg)ExternalProcessi+zAStep environment in a separate process for lock free paralellism.r<rmc[R"5uUln[R"URX4S9Ul[ R"UR5 UR R5 SUl SUl g)a#Step environment in a separate process for lock free paralellism. The environment will be created in the external process by calling the specified callable. This can be an environment class, or a function creating the environment and potentially wrapping it. The returned environment should not access global variables. Args: constructor: Callable that creates and returns an OpenAI gym environment. Attributes: observation_space: The cached observation space of the environment. action_space: The cached action space of the environment. )targetargsN) multiprocessingPipe_connProcess_worker_processatexitregisterclosestart _observ_space _action_space)r constructorconns rrExternalProcess.__init__8sd'++-DJ#++4<<{FYZDM OODJJMMDDrchUR(dURS5UlUR$)Nrn)rrr(s rrn!ExternalProcess.observation_spaceNs+   ++,?@d   rchUR(dURS5UlUR$)NrO)rrr(s rrOExternalProcess.action_spaceTs*   ++N;d   rcURRURU45 URUR5$)zRequest an attribute from the environment. Note that this involves communication with the external process, so it can be slow. Args: name: Attribute to access. Returns: Value of the attribute. )rsend _ATTRIBUTE_receive_VALUErs rrExternalProcess.__getattr__Zs0 JJOOT__d+, == %%rcURRURU45 U(aURUR5$[ R "URUR5$)zStep the environment. Args: action: The action to apply to the environment. blocking: Whether to wait for the result. Returns: Transition tuple when blocking, otherwise callable that returns the transition tuple. )rr_ACTIONr _TRANSITION functoolspartial)r r!blockings rrExternalProcess.stepisR JJOOT\\6*+ ]]4++ ,,   t}}d.>.> ??rcURRURS45 U(aURUR5$[ R "URUR5$)zReset the environment. Args: blocking: Whether to wait for the result. Returns: New observation when blocking, otherwise callable that returns the new observation. N)rr_RESETr_OBSERVrr)r rs rrExternalProcess.resetzsN JJOOT[[$'( ]]4<< ((   t}}dll ;;rcURRURS45 URR5 UR R 5 g![a N'f=f)z9Send a close message to the external process and join it.N)rr_CLOSErIOErrorrjoinr(s rrExternalProcess.closesV  jjoot{{D)* jj MM    sAA A+*A+cURR5up#X R:Xa Un[U5eX!:XaU$[ SR U55e)a.Wait for a message from the worker process and return its payload. Args: expected_message: Type of the expected message. Raises: Exception: An exception was raised inside the worker process. KeyError: The reveived message is not of the expected type. Returns: Payload object of the message. z&Received message of unexpected type {})rrecv _EXCEPTION Exceptionr]format)r expected_messagemessagepayload stacktraces rrExternalProcess._receivesSzz(G//!j j !!" n ;BB7K LLrcU"5nURS5(dMUR5upEX@R:Xa0UnUR UR URU545 MkX@R:Xa2UbeUR URUR545 MX@R:Xa*UnUR UR[X7545 MX@R:XaUbeO[SR!U55eUR75 g![[4a M$f=f!["a SR%[&R("[*R,"565nUR UR.U45 [0R2R5SR!U55 Nf=f)zThe process waits for actions and sends back environment results. Args: constructor: Constructor for the OpenAI Gym environment. conn: Connection for communication to the main process. g?Nz#Received message of unknown type {}z Error in environment process: {})pollrEOFErrorKeyboardInterruptrrrrrrrrrrrr]r r r tracebackformat_exceptionsysexc_inforrQrRerrorr) r rrrr r r!rrs rrExternalProcess._workers~N Mc  3 !YY[ ' ll "& ))T%%sxx'78 9  kk !  ))T\\399;/ 0  oo %$ ))T[['#"45 6  kk !  <CCGLMM  JJL-+,   $ N77955s||~FGj ii*-.jj9@@LMNsEED.ED.C EE.E>EEEB GG)rrrrN)T)r+r,r-r.r/rrrrrrrrrrrnrOrrrrrrr0r1rrrr+s|I ' & &*+ '* &,      &@"< M,%rrc<\rSrSrSrSrSrSrSrSr Sr S r g ) ConvertTo32Bitiz:Convert data types of an OpenAI Gym environment to 32 bit.cXlg)zaConvert data types of an OpenAI Gym environment to 32 bit. Args: env: OpenAI Gym environment. Nrr s rrConvertTo32Bit.__init__s Irc.[URU5$)zForward unimplemented attributes to the original environment. Args: name: Attribute that was accessed. Returns: Value behind the attribute name in the wrapped environment. rrs rrConvertTo32Bit.__getattr__s 499d ##rcURRU5up#pEURU5nURU5nX#XE4$)zForward action to the wrapped environment. Args: action: Action to apply to the environment. Raises: ValueError: Invalid action. Returns: Converted observation, converted reward, done flag, and info object. )r r_convert_observ_convert_rewardr s rrConvertTo32Bit.stepsF"&!7FD  ! !& )F  ! !& )F 4 %%rc\URR5nURU5nU$)z`Reset the environment and convert the resulting observation. Returns: Converted observation. )r rr"r~s rrConvertTo32Bit.resets) YY__ F  ! !& )F Mrcb[R"U5R5(d [S5eUR[R :XaUR [R5$UR[R:XaUR [R5$U$)zConvert the observation to 32 bits. Args: observ: Numpy observation. Raises: ValueError: Observation contains infinite values. Returns: Numpy observation with 32-bit data type. z!Infinite observation encountered.) rKrrrdtypefloat64astypefloat32int64int32r~s rr"ConvertTo32Bit._convert_observss ;;v  " " $ $ : ;; ||rzz! ]]2:: && ||rxx ]]288 $$ Mrc[R"U5R5(d [S5e[R"U[R S9$)zConvert the reward to 32 bits. Args: reward: Numpy reward. Raises: ValueError: Rewards contain infinite values. Returns: Numpy reward with 32-bit data type. zInfinite reward encountered.)r()rKrrrarrayr+)r r#s rr#ConvertTo32Bit._convert_rewards= ;;v  " " $ $ 5 66 88F"** --rrN) r+r,r-r.r/rrrrr"r#r0r1rrrrs#B $&"(.rr)r/ __future__rrrrrrrrru gym.spacesnumpyrK tf.compat.v1compatv1rQobjectrr3rArZrrrrrrr1rrr9s,&%   .,6,*&,:6:z:>JV>JB""(F4dfdNS.VS.r