[doc] fix: formatting issue for kl_ctrl and fused_kernel_options configs (volcengine#3917)

### What does this PR do?

> Add **concise** overview of what this PR aims to achieve or
accomplish. Reference related GitHub issues and PRs that help with the
review.

<img width="1295" height="152" alt="image"
src="https://github.com/user-attachments/assets/3c9de645-da2a-43ea-93fc-2a41480091bd"
/>

<img width="1301" height="100" alt="image"
src="https://github.com/user-attachments/assets/a71259ce-6e26-45ee-8387-6c2a3d0ab412"
/>


Add line breaks before and after the second level list.

### Checklist Before Starting

- [X] Search for similar PRs. Paste at least one query link here: ...
- [X] Format the PR title as `[{modules}] {type}: {description}` (This
will be checked by the CI)
- `{modules}` include `fsdp`, `megatron`, `sglang`, `vllm`, `rollout`,
`trainer`, `ci`, `training_utils`, `recipe`, `hardware`, `deployment`,
`ray`, `worker`, `single_controller`, `misc`, `perf`, `model`, `algo`,
`env`, `tool`, `ckpt`, `doc`, `data`
- If this PR involves multiple modules, separate them with `,` like
`[megatron, fsdp, doc]`
  - `{type}` is in `feat`, `fix`, `refactor`, `chore`, `test`
- If this PR breaks any API (CLI arguments, config, function signature,
etc.), add `[BREAKING]` to the beginning of the title.
  - Example: `[BREAKING][fsdp, megatron] feat: dynamic batching`

### Test

> For changes that can not be tested by CI (e.g., algorithm
implementation, new model support), validate by experiment(s) and show
results like training curve plots, evaluation results, etc.

### API and Usage Example

> Demonstrate how the API changes if any, and provide usage example(s)
if possible.

```python
# Add code snippet or script demonstrating how to use this
```

### Design & Code Changes

> Demonstrate the high-level design if this PR is complex, and list the
specific changes.

### Checklist Before Submitting

> [!IMPORTANT]
> Please check all the following items before requesting a review,
otherwise the reviewer might deprioritize this PR for review.

- [X] Read the [Contribute
Guide](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md).
- [X] Apply [pre-commit
checks](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md#code-linting-and-formatting):
`pre-commit install && pre-commit run --all-files --show-diff-on-failure
--color=always`
- [X] Add / Update [the
documentation](https://github.com/volcengine/verl/tree/main/docs).
- [X] Add unit or end-to-end test(s) to [the CI
workflow](https://github.com/volcengine/verl/tree/main/.github/workflows)
to cover all the code. If not feasible, explain why: ...
- [X] Once your PR is ready for CI, send a message in [the `ci-request`
channel](https://verl-project.slack.com/archives/C091TCESWB1) in [the
`verl` Slack
workspace](https://join.slack.com/t/verl-project/shared_invite/zt-3855yhg8g-CTkqXu~hKojPCmo7k_yXTQ).
(If not accessible, please try [the Feishu group
(飞书群)](https://applink.larkoffice.com/client/chat/chatter/add_by_link?link_token=772jd4f1-cd91-441e-a820-498c6614126a).)

Signed-off-by: Hollow Man <[email protected]>

Author: HollowMan6

docs/examples/config.rst

@@ -237,11 +237,13 @@ Actor/Rollout/Reference Policy
 - ``actor_rollout_ref.model.use_fused_kernels``: Whether to use fused
   kernels in the model. If set to True, the following parameters will be
   used.
+
   - ``actor_rollout_ref.model.fused_kernel_options.impl_backend``: The
-  implementation backend for fused kernels. Options: "triton" or
-  "torch". Default is "torch".
-  While in megatron, we only support "triton" as the
-  implementation backend, so there is no need for this option.
+    implementation backend for fused kernels. Options: "triton" or
+    "torch". Default is "torch".
+    While in megatron, we only support "triton" as the
+    implementation backend, so there is no need for this option.
+
 - ``actor_rollout_ref.model.use_remove_padding``: Whether to use remove
   padding in the model. If set to True, the model will remove padding
   tokens in the input_ids and response_ids. This helps a lot in improving model running efficiency.
@@ -529,9 +531,11 @@ Algorithm
   calculate the kl divergence between actor and reference policy. For
   specific options, refer to `kl_penalty()` in `core_algos.py <https://github.com/volcengine/verl/blob/main/verl/trainer/ppo/core_algos.py>`_ .
 - ``kl_ctrl``: Config for in-reward kl_penalty controller
+
   - ``kl_coef``: The (initial) coefficient of in-reward kl_penalty. Default is 0.001.
   - ``type``: 'fixed' for FixedKLController and 'adaptive' for AdaptiveKLController.
   - ``horizon`` and ``target_kl``: See source code of AdaptiveKLController for details.
+
 - ``rollout_is``: Whether to enable rollout importance sampling correction. Default is False.
 - ``rollout_is_threshold``: Upper threshold for IS weights. Set to ``null`` to disable IS completely.
 - ``rollout_is_threshold_lower``: Lower threshold for IS weights. If ``null``, defaults to reciprocal of upper (1/upper).