h SrSSKJr SSKJr SSKJr SSKrSSK r SSK J r J r SSKJr SS /r"S S\ R"\ \ 4\ R$R&5r"S S \\ \ 4\ R$R&5rg) zA collection of wrappers for modifying the reward. * ``TransformReward`` - Transforms the reward by a function * ``ClipReward`` - Clips the reward between a minimum and maximum value ) annotations)Callable) SupportsFloatN)ActTypeObsType) InvalidBoundTransformReward ClipRewardc4\rSrSrSrSSjrSSjrSrg) r aApplies a function to the ``reward`` received from the environment's ``step``. A vector version of the wrapper exists :class:`gymnasium.wrappers.vector.TransformReward`. Example: >>> import gymnasium as gym >>> from gymnasium.wrappers import TransformReward >>> env = gym.make("CartPole-v1") >>> env = TransformReward(env, lambda r: 2 * r + 1) >>> _ = env.reset() >>> _, rew, _, _, _ = env.step(0) >>> rew 3.0 Change logs: * v0.15.0 - Initially added c[RRRXS9 [RRX5 X lg)zInitialize TransformReward wrapper. Args: env (Env): The environment to wrap func: (Callable): The function to apply to reward funcN)gymutilsRecordConstructorArgs__init__ RewardWrapperr)selfenvrs ]/home/james-whalen/.local/lib/python3.13/site-packages/gymnasium/wrappers/transform_reward.pyrTransformReward.__init__+s8 ''000A ""4- c$URU5$)zbApply function to reward. Args: reward (Union[float, int, np.ndarray]): environment's reward r)rrewards rrTransformReward.reward;s yy  rrN)rgym.Env[ObsType, ActType]rz(Callable[[SupportsFloat], SupportsFloat])rrreturnr)__name__ __module__ __qualname____firstlineno____doc__rr__static_attributes__rrr r s#$ &7 !rc4\rSrSrSrSSSjjrSrg)r DaClips the rewards for an environment between an upper and lower bound. A vector version of the wrapper exists :class:`gymnasium.wrappers.vector.ClipReward`. Example: >>> import gymnasium as gym >>> from gymnasium.wrappers import ClipReward >>> env = gym.make("CartPole-v1") >>> env = ClipReward(env, 0, 0.5) >>> _ = env.reset() >>> _, rew, _, _, _ = env.step(1) >>> rew np.float64(0.5) Change logs: * v1.0.0 - Initially added Nc ^^TcTc [S5eTb6Tb3[R"TT- S:5(a[STSTS35e[RR R UTTS9 [R XUU4SjS 9 g) zInitialize ClipRewards wrapper. Args: env (Env): The environment to wrap min_reward (Union[float, np.ndarray]): lower bound to apply max_reward (Union[float, np.ndarray]): higher bound to apply Nz1Both `min_reward` and `max_reward` cannot be Nonerz Min reward (z#) must be smaller than max reward ()) min_reward max_rewardc0>[R"UTTS9$)N)a_mina_max)npclip)xr+r*s r%ClipReward.__init__..qs"''!:Z*Xr)rr)rr/anyrrrrr )rrr*r+s ``rrClipReward.__init__Ws  *"4RS S  # (>vvj:-122"":,.QR\Q]]^_ ''00 ZJ 1     X ! rr%)NN)rrr*float | np.ndarray | Noner+r6)rr r!r"r#rr$r%rrr r Ds5*1504  & . .   r)r# __future__rcollections.abcrtypingrnumpyr/ gymnasiumrgymnasium.corerrgymnasium.errorr__all__rrrr r r%rrr?sy #$ +( l ++!gw&')H)H+!\. '!12CII4S4S. r