fix(embodiment): apply SFT loss in co-training (#1368) (#1381)

Signed-off-by: bianhua-12 <1983908224@qq.com>
Co-authored-by: Shuaihang Chen <1983908224@qq.com>

docs: add release notes (#936)

* docs: add release note for v0.1 and v0.2

---------

Signed-off-by: xusi <xusi@infinis-ai.com>
Co-authored-by: xusi <xusi@infinis-ai.com>

Release RLinf v0.1

Pre-release snapshot for v0.1