HF RL Explorer

Add a get cosine scaled reward factory function to trl/rewards and export it from trl.rewards .

Add a get cosine scaled reward factory function to trl/rewards and export it from trl.rewards .: a task in HF ML Tasksmith (Harbor dataset). The function signature is: python def get cosine scaled reward( max len: int, min value wrong: float = -1.0, max value wrong: float = -0.5, min value…

Part of FineEnvs/HF_ML_Tasksmith.