fast_profit_reward
==================

.. py:module:: fast_profit_reward

.. autoapi-nested-parse::

   Fast reward function optimized for training speed.
   Does not maintain any history or complex calculations.



Classes
-------

.. autoapisummary::

   fast_profit_reward.FastProfitReward
   fast_profit_reward.SimpleMomentumReward


Module Contents
---------------

.. py:class:: FastProfitReward(cfg, initial_state)

   Bases: :py:obj:`trading.src.alg.environments.reward_functions.base_reward_function.RewardFunction`


   Ultra-fast reward function that only considers immediate portfolio value change.
   No history tracking, no complex metrics. Perfect for fast training.


   .. py:attribute:: previous_value


   .. py:method:: __repr__()


   .. py:method:: reset()

      Reset reward state.



   .. py:method:: compute_reward(pf, df, realized_profit)

      Compute reward based on simple portfolio value change.

      :param pf: Portfolio object (we extract net_value)
      :param df: DataFrame (not used in fast mode)
      :param realized_profit: Realized profit from trades (not used in fast mode)

      :returns: Normalized reward value



.. py:class:: SimpleMomentumReward(cfg, initial_state)

   Bases: :py:obj:`trading.src.alg.environments.reward_functions.base_reward_function.RewardFunction`


   Reward based on price momentum (change in portfolio value relative to price movement).
   Still fast but slightly more sophisticated than pure profit.


   .. py:attribute:: previous_value


   .. py:method:: __repr__()


   .. py:method:: reset()

      Reset reward state.



   .. py:method:: compute_reward(pf, df, realized_profit)

      Compute reward that emphasizes profit relative to portfolio size.
      Encourages growing the portfolio while being mindful of risk.

      :param pf: Portfolio object
      :param df: DataFrame (not used)
      :param realized_profit: Realized profit from trades

      :returns: Normalized reward value