Fix/replace slices with string

[LinghengMeng]

Description

This request is to fix the problem of running Isaac-Stack-Cube-Franka-v0 with rsl_rl PPO.

The changes are around the Isaac-Stack-Cube-Franka-v0:

• replace_slices_with_strings() and replace_strings_with_slices() in IsaacLab/source/isaaclab/isaaclab/utils/dict.py are changed to allow slices being process if a list of dicts is passed in as input.
• add rsl_rl_ppo_cfg.py to Isaac-Stack-Cube-Franka-v0 and update gym.register
• set concatenate_terms to True in IsaacLab/source/isaaclab_tasks/isaaclab_tasks/manager_based/manipulation/stack/stack_env_cfg.py. Otherwise, RL lib following Gymnasium API will not work when setting up observation dimension with obs_dim = obs.shape[1]

To test, run the following:

cd IsaacLab
./isaaclab.sh -p ./scripts/reinforcement_learning/rsl_rl/train.py --task Isaac-Stack-Cube-Franka-v0  --num_envs 10

Note: Because there is no RewardCfg for this task, there will be no learning progress. This can only check the task can be run without any problem.

Fixes #2481

Type of change

• Bug fix (non-breaking change which fixes an issue)

Screenshots

• Change 1: replace_slices_with_strings() and replace_strings_with_slices() in IsaacLab/source/isaaclab/isaaclab/utils/dict.py

Before	After

• Change 2: add rsl_rl_ppo_cfg.py to Isaac-Stack-Cube-Franka-v0 and update gym.register

Before	After

• Change 3: set concatenate_terms to True in IsaacLab/source/isaaclab_tasks/isaaclab_tasks/manager_based/manipulation/stack/stack_env_cfg.py. Otherwise, RL lib following Gymnasium API will not work when setting up observation dimension with obs_dim = obs.shape[1]

Before	After

Checklist

• I have run the pre-commit checks with ./isaaclab.sh --format
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• I have updated the changelog and the corresponding version in the extension's config/extension.toml file
• I have added my name to the CONTRIBUTORS.md or my name already exists there

[kellyguo11]

I think if we want to add a RL agent cfg for the task, would be good to also extend the task to allow for learning.

[kellyguo11]

might make sense to separate these changes apart from the environment updates so that we can merge these in individually.