hSrSSKJr SSKJr SSKJr SSKrSSK J r SSK J r J r SSKJr SS KJr "S S \ 5r"S S \ 5r"SS\5rg)z4Vectorizes reward function to work with `VectorEnv`.) annotations)Callable)AnyN)Env) VectorEnvVectorRewardWrapper) ArrayType)transform_rewardc:^\rSrSrSrSU4SjjrSSjrSrU=r$)TransformRewardaA reward wrapper that allows a custom function to modify the step reward. Example with reward transformation: >>> import gymnasium as gym >>> from gymnasium.spaces import Box >>> def scale_and_shift(rew): ... return (rew - 1.0) * 2.0 ... >>> envs = gym.make_vec("MountainCarContinuous-v0", num_envs=3) >>> envs = TransformReward(env=envs, func=scale_and_shift) >>> _ = envs.action_space.seed(123) >>> obs, info = envs.reset(seed=123) >>> obs, rew, term, trunc, info = envs.step(envs.action_space.sample()) >>> envs.close() >>> obs array([[-4.6343064e-01, 9.8971417e-05], [-4.4488689e-01, -1.9375233e-03], [-4.3118435e-01, -1.5342437e-03]], dtype=float32) c0>[TU]U5 X lg)zInitialize LambdaReward wrapper. Args: env (Env): The vector environment to wrap func: (Callable): The function to apply to reward N)super__init__func)selfenvr __class__s d/home/james-whalen/.local/lib/python3.13/site-packages/gymnasium/wrappers/vector/vectorize_reward.pyrTransformReward.__init__%s  c$URU5$)zApply function to reward.r)rrewards rrewardsTransformReward.rewards0syy  rr)rrrz Callable[[ArrayType], ArrayType]rr returnr __name__ __module__ __qualname____firstlineno____doc__rr__static_attributes__ __classcell__rs@rr r s( !!rr cF^\rSrSrSrSU4SjjrSSjrSrU=r$)VectorizeTransformReward5aYVectorizes a single-agent transform reward wrapper for vector environments. An example such that applies a ReLU to the reward: >>> import gymnasium as gym >>> from gymnasium.wrappers import TransformReward >>> envs = gym.make_vec("MountainCarContinuous-v0", num_envs=3) >>> envs = VectorizeTransformReward(envs, wrapper=TransformReward, func=lambda x: (x > 0.0) * x) >>> _ = envs.action_space.seed(123) >>> obs, info = envs.reset(seed=123) >>> obs, rew, term, trunc, info = envs.step(envs.action_space.sample()) >>> envs.close() >>> rew array([-0., -0., -0.]) c P>[TU]U5 U"[540UD6Ulg)zConstructor for the vectorized lambda reward wrapper. Args: env: The vector environment to wrap. wrapper: The wrapper to vectorize **kwargs: Keyword argument for the wrapper N)rrrwrapper)rrr,kwargsrs rr!VectorizeTransformReward.__init__Es% su// rch[U5H"up#URRU5X'M$ U$)z=Iterates over the reward updating each with the wrapper func.) enumerater,r)rrirs rr VectorizeTransformReward.rewardsVs.f%DA ))!,FI& r)r,)rrr,z&type[transform_reward.TransformReward]r-rrrr's@rr)r)5s3 0 080 0"rr)cB^\rSrSrSrSSU4SjjjrSrU=r$) ClipReward]aA wrapper that clips the rewards for an environment between an upper and lower bound. Example with clipped rewards: >>> import numpy as np >>> import gymnasium as gym >>> envs = gym.make_vec("MountainCarContinuous-v0", num_envs=3) >>> envs = ClipReward(envs, 0.0, 2.0) >>> _ = 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() >>> rew array([0., 0., 0.]) cB>[TU]U[RUUS9 g)zConstructor for ClipReward wrapper. Args: env: The vector environment to wrap min_reward: The min reward for each step max_reward: the max reward for each step ) min_reward max_rewardN)rrr r5)rrr8r9rs rrClipReward.__init__os)    ' '!!  r)NN)rrr8float | np.ndarray | Noner9r<)r r!r"r#r$rr%r&r's@rr5r5]s6(1504   . .   rr5)r$ __future__rcollections.abcrtypingrnumpynp gymnasiumrgymnasium.vectorrrgymnasium.vector.vector_envr gymnasium.wrappersr r r)r5r;rrrFsI:"$;1/"!)"!J%2%P$ )$ r