[RLlib] Don't modify SampleBatch in place when counting

[ArturNiederfahrenhorst]

Signed-off-by: Artur Niederfahrenhorst [email protected]

Why are these changes needed?

We currently modify the original sample batch in place when counting instead of the copy. (We make everything except SampleBatch.SEQ_LENS an np.array)

Checks

• [x] I've signed off every commit(by using the -s flag, i.e., git commit -s) in this PR.
• [x] 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 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
  • [x] This PR is not tested :(