Reinforcement learning (RL)
===========================

.. currentmodule:: tunix

.. autosummary::

    GRPOConfig
    GRPOLearner
    RewardFn

    PPOConfig
    PPOLearner

    ClusterConfig
    RLEngine
    RLTrainingConfig
    Role
    RolloutConfig

-------

.. autoclass:: GRPOConfig

-------

.. autoclass:: GRPOLearner

-------

.. autoclass:: RewardFn

-------

.. autoclass:: PPOConfig

-------

.. autoclass:: PPOLearner

-------


.. autoclass:: ClusterConfig

-------

.. autoclass:: RLEngine

-------

.. autoclass:: RLTrainingConfig

-------

.. autoclass:: Role

-------

.. autoclass:: RolloutConfig

