Refactor DP

[gaodechen]

Description

• Separate DP/FM/VITA
• Move all diffusion_policy utils, utils.common to il/utils
• Remove repeated source codes from diffusion_policy and merge into DP
• Move base/configs/runner to the top-level IL folder as they are supposed to be shared by all policies
• Each policy is as self-contained as possible (as suggested by roboverse_learn document) while sharing minimum abstractions for easier maintainance
• Creating a separate README for each policy

How to test

bash roboverse_learn/il/il_run.sh --task_name_set close_box --algo_choose ddpm_dit
bash roboverse_learn/il/il_run.sh --task_name_set close_box --algo_choose ddpm_unet
bash roboverse_learn/il/il_run.sh --task_name_set close_box --algo_choose fm_dit
bash roboverse_learn/il/il_run.sh --task_name_set close_box --algo_choose fm_unet
bash roboverse_learn/il/il_run.sh --task_name_set close_box --algo_choose vita
bash roboverse_learn/il/il_run.sh --task_name_set close_box --algo_choose score
bash roboverse_learn/il/il_run.sh --task_name_set close_box --algo_choose act

Checklist

• [ x] I have run the pre-commit checks with pre-commit run --color=always --all-files
• [ x] I have made corresponding changes to the documentation
• [ x] My changes generate no new warnings
• [ x] I have added tests that prove my fix is effective or that my feature works
• [ x] I have added my name to the CONTRIBUTORS.md or my name already exists there