callbacks.training_telemetry
============================

.. py:module:: callbacks.training_telemetry

.. autoapi-nested-parse::

   Enhanced telemetry callback for detailed training insights.
   Tracks portfolio metrics, action distributions, and trading patterns.



Classes
-------

.. autoapisummary::

   callbacks.training_telemetry.TradingTelemetryCallback


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

.. py:class:: TradingTelemetryCallback(verbose = 0, log_freq = 256, action_threshold = 0.1)

   Bases: :py:obj:`stable_baselines3.common.callbacks.BaseCallback`


   Custom callback for tracking detailed trading metrics during training.

   Logs:
   - Portfolio value and equity changes
   - Action statistics (buy/sell/hold distribution)
   - Episode-level metrics (win rate, drawdown)
   - Per-ticker performance insights


   .. py:attribute:: log_freq
      :value: 256



   .. py:attribute:: action_threshold
      :value: 0.1



   .. py:attribute:: episode_rewards
      :type:  list[float]
      :value: []



   .. py:attribute:: episode_lengths
      :type:  list[int]
      :value: []



   .. py:attribute:: episode_equity_start
      :type:  list[float]
      :value: []



   .. py:attribute:: episode_equity_end
      :type:  list[float]
      :value: []



   .. py:attribute:: action_history
      :type:  list[numpy.ndarray]
      :value: []



   .. py:attribute:: buy_count
      :value: 0



   .. py:attribute:: sell_count
      :value: 0



   .. py:attribute:: hold_count
      :value: 0



   .. py:attribute:: max_portfolio_value
      :value: 0



   .. py:attribute:: min_portfolio_value


   .. py:attribute:: cumulative_trades
      :value: 0



   .. py:attribute:: current_episode_start_value
      :value: None



   .. py:method:: _on_training_start()

      Called before the first rollout starts.



   .. py:method:: _on_rollout_start()

      Called at the beginning of a new rollout (before collecting data).



   .. py:method:: _on_step()

      Called after each step in the environment.

      :returns: If False, training will be stopped.
      :rtype: bool



   .. py:method:: _on_rollout_end()

      Called at the end of a rollout (after collecting n_steps).
      This is when PPO does its policy update.



   .. py:method:: _log_detailed_metrics()

      Log detailed metrics about training progress.



   .. py:method:: _on_training_end()

      Called at the end of training.