[doc] fix: edit one step off policy readme with original work (volcengine#3414)

### What does this PR do?

Updates the readme for the one-step off-policy async trainer with the
original reference paper

I introduced async RL training for LLMs in my paper
https://arxiv.org/abs/2410.18252. My method is exactly the one step
off-policy async replicated here and was on arxiv 7 months before AReal
and published at ICLR. AReal's method is different (fully async replay
buffer) but it includes a nice graphic of my setup!

Love to see you're getting similar speedups to my results and this is a
great recipe!

Figure 2 from my paper

<img width="1040" height="611" alt="image"
src="https://github.com/user-attachments/assets/0812fd40-daae-4346-bb72-85bc526bd3fa"
/>

### Checklist Before Starting

- [x] Search for similar PRs. Paste at least one query link here:
volcengine#2591
- [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`

### 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).)

Author: mnoukhov

recipe/one_step_off_policy/README.md

@@ -35,6 +35,7 @@ policy.
 https://raw.githubusercontent.com/eric-haibin-lin/verl-community/refs/heads/main/docs/one_step_off_policy.png)
 > reference: [AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning](
 > https://arxiv.org/abs/2505.24298)
+> original work: [Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models](https://arxiv.org/abs/2410.18252)
 
 Our core contributions include: