[worker] fix: Fix missing rollout_log_probs argument in policy loss functions (volcengine#3274)

### 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.
-->

In the recent PR:

- volcengine#2953,

the file `workers/actor/dp_actor.py` was updated so that
`rollout_log_probs` is passed to `policy_loss_fn`:


https://github.com/volcengine/verl/blob/38d23914ee512a125e00763fe3ddcc8df4319346/verl/workers/actor/dp_actor.py#L448-L456

In that PR, the "vanilla" policy loss function was modified to accept
`rollout_log_probs` as an argument. However, other policy loss functions
(e.g., "gspo") were not updated accordingly, which leads to an error
such as:

```
TypeError: compute_policy_loss_gspo() got an unexpected keyword argument 'rollout_log_probs'
```

when setting `config.policy_loss.loss_mode` to one of these
alternatives.

Therefore, in this PR, `rollout_log_probs` is also added as an argument
to the other policy loss functions.



### 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).)

Author: kAIto47802

verl/trainer/ppo/core_algos.py

@@ -41,6 +41,7 @@
         torch.Tensor,  # response_mask
         str,  # loss_agg_mode
         Optional[DictConfig | AlgoConfig],  # config
+        torch.Tensor | None,  # rollout_log_probs
     ],
     tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor],
 ]
@@ -820,7 +821,7 @@ def compute_policy_loss_vanilla(
     response_mask: torch.Tensor,
     loss_agg_mode: str = "token-mean",
     config: Optional[DictConfig | AlgoConfig] = None,
-    rollout_log_probs=None,
+    rollout_log_probs: torch.Tensor | None = None,
 ) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]:
     """
     Compute the clipped policy objective and related metrics for PPO.
@@ -909,6 +910,7 @@ def compute_policy_loss_gspo(
     response_mask: torch.Tensor,
     loss_agg_mode: str = "seq-mean-token-mean",
     config: Optional[DictConfig | ActorConfig] = None,
+    rollout_log_probs: torch.Tensor | None = None,
 ) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]:
     """
     Compute the clipped policy objective and related metrics for GSPO.
@@ -967,7 +969,15 @@ def compute_policy_loss_gspo(
 
 
 @register_policy_loss("gpg")
-def compute_policy_loss_gpg(old_log_prob, log_prob, advantages, response_mask, loss_agg_mode="token-mean", config=None):
+def compute_policy_loss_gpg(
+    old_log_prob: torch.Tensor,
+    log_prob: torch.Tensor,
+    advantages: torch.Tensor,
+    response_mask: torch.Tensor,
+    loss_agg_mode: str = "token-mean",
+    config: Optional[DictConfig | AlgoConfig] = None,
+    rollout_log_probs: torch.Tensor | None = None,
+) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]:
     """Adapted from
     https://github.com/AMAP-ML/GPG/blob/main/VisualThinker-R1-Zero/src/open-r1-multimodal/src/open_r1/trainer/grpo_trainer.py#L495
     Args:
@@ -995,6 +1005,7 @@ def compute_policy_loss_clip_cov(
     response_mask: torch.Tensor,
     loss_agg_mode: str = "token-mean",
     config: Optional[DictConfig | AlgoConfig] = None,
+    rollout_log_probs: torch.Tensor | None = None,
 ) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]:
     """
     Compute the clipped policy objective and related metrics for Clip-Cov.
@@ -1089,6 +1100,7 @@ def compute_policy_loss_kl_cov(
     response_mask: torch.Tensor,
     loss_agg_mode: str = "token-mean",
     config: Optional[DictConfig | AlgoConfig] = None,
+    rollout_log_probs: torch.Tensor | None = None,
 ) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]:
     """
     Compute the clipped policy objective and related metrics for Clip-Cov.
@@ -1160,6 +1172,7 @@ def compute_policy_loss_geo_mean(
     response_mask: torch.Tensor,
     loss_agg_mode: str = "token-mean",
     config: Optional[DictConfig | AlgoConfig] = None,
+    rollout_log_probs: torch.Tensor | None = None,
 ) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]:
     """
     Compute the clipped policy objective and related metrics for GMPO.