Add RL training configs, scripts, and environment updates

[nikhilk7153]

• Add GRPO training configs for MedCalc-Bench, MedMCQA, MedCaseReasoning, and combined training
• Add plotting scripts for training curves and evaluation results
• Add model evaluation and HuggingFace upload scripts
• Update environment files with improvements for RL training

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
1 out of 2 committers have signed the CLA.

✅ nikhilk7153
❌ Nikhil Khandekar

---

Nikhil Khandekar seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}