# {py:mod}`evorl.envs.wrappers.reward_wrapper`

```{py:module} evorl.envs.wrappers.reward_wrapper
```

```{autodoc2-docstring} evorl.envs.wrappers.reward_wrapper
:parser: autodoc2_docstrings_parser
:allowtitles:
```

## Module Contents

### Classes

````{list-table}
:class: autosummary longtable
:align: left

* - {py:obj}`RewardScaleWrapper <evorl.envs.wrappers.reward_wrapper.RewardScaleWrapper>`
  - ```{autodoc2-docstring} evorl.envs.wrappers.reward_wrapper.RewardScaleWrapper
    :parser: autodoc2_docstrings_parser
    :summary:
    ```
* - {py:obj}`SparseRewardWrapper <evorl.envs.wrappers.reward_wrapper.SparseRewardWrapper>`
  - ```{autodoc2-docstring} evorl.envs.wrappers.reward_wrapper.SparseRewardWrapper
    :parser: autodoc2_docstrings_parser
    :summary:
    ```
````

### API

`````{py:class} RewardScaleWrapper(env: evorl.envs.env.Env, reward_scale: float)
:canonical: evorl.envs.wrappers.reward_wrapper.RewardScaleWrapper

Bases: {py:obj}`evorl.envs.wrappers.wrapper.Wrapper`

```{autodoc2-docstring} evorl.envs.wrappers.reward_wrapper.RewardScaleWrapper
:parser: autodoc2_docstrings_parser
```

````{py:method} reset(key: chex.PRNGKey) -> evorl.envs.env.EnvState
:canonical: evorl.envs.wrappers.reward_wrapper.RewardScaleWrapper.reset

````

````{py:method} step(state: evorl.envs.env.EnvState, action: evorl.types.Action) -> evorl.envs.env.EnvState
:canonical: evorl.envs.wrappers.reward_wrapper.RewardScaleWrapper.step

````

`````

`````{py:class} SparseRewardWrapper(env: evorl.envs.env.Env, sparse_length: int)
:canonical: evorl.envs.wrappers.reward_wrapper.SparseRewardWrapper

Bases: {py:obj}`evorl.envs.wrappers.wrapper.Wrapper`

```{autodoc2-docstring} evorl.envs.wrappers.reward_wrapper.SparseRewardWrapper
:parser: autodoc2_docstrings_parser
```

````{py:method} reset(key: chex.PRNGKey) -> evorl.envs.env.EnvState
:canonical: evorl.envs.wrappers.reward_wrapper.SparseRewardWrapper.reset

````

````{py:method} step(state: evorl.envs.env.EnvState, action: evorl.types.Action) -> evorl.envs.env.EnvState
:canonical: evorl.envs.wrappers.reward_wrapper.SparseRewardWrapper.step

````

`````