fix restore BUG "RuntimeError: Expected scalars to be on CPU, got cud…

[a416297338]

Why are these changes needed?

When performing a restore, the error RuntimeError: Expected scalars to be on CPU, got cuda:0 instead occurs, similar to the situation in #34159. However, in the older version, the modification was made in the policy, while in the newer version, it needs to be adjusted in torch_learner.

Related issue number

Similar to #34159

Checks

• I've signed off every commit(by using the -s flag, i.e., git commit -s) in this PR.
• I've run scripts/format.sh to lint the changes in this PR.
• I've included any doc changes needed for https://docs.ray.io/en/master/.
  • I've added any new APIs to the API Reference. For example, if I added a
    method in Tune, I've added it in doc/source/tune/api/ under the
    corresponding .rst file.
• I've made sure the tests are passing. Note that there might be a few flaky tests, see the recent failures at https://flakey-tests.ray.io/
• Testing Strategy
  • Unit tests
  • Release tests
  • This PR is not tested :(

[a416297338]

@sven1977 thanks for you reivew