diff --git a/docs/source/custom_agent.rst b/docs/source/custom_agent.rst index 53594a8f..74b6a607 100644 --- a/docs/source/custom_agent.rst +++ b/docs/source/custom_agent.rst @@ -4,7 +4,7 @@ **Integrating a user defined blue agent** -PrimAITE has integration with Ray RLLib and StableBaselines3 agents. All agents interface with PrimAITE through an :py:class:`primaite.agents.agent.AgentSessionABC` which provides Input/Output of agent savefiles, as well as capturing and plotting performance metrics during training. If you wish to integrate a custom blue agent, it is recommended to create a subclass of the :py:class:`primaite.agents.agent.AgentSessionABC` and implement the ``__init__()``, ``_setup()``, ``_save_checkpoint()``, ``learn()``, ``evaluate()``, ``_get_latest_checkpoint``, ``load()``, ``save()``, and ``export()`` methods. You will also need to modify :py:class:`primaite.primaite_session.PrimaiteSession` class to capture your new agent identifier. +PrimAITE has integration with Ray RLLib and StableBaselines3 agents. All agents interface with PrimAITE through an :py:class:`primaite.agents.agent.AgentSessionABC` which provides Input/Output of agent savefiles, as well as capturing and plotting performance metrics during training. If you wish to integrate a custom blue agent, it is recommended to create a subclass of the :py:class:`primaite.agents.agent.AgentSessionABC` and implement the ``__init__()``, ``_setup()``, ``_save_checkpoint()``, ``learn()``, ``evaluate()``, ``_get_latest_checkpoint``, ``load()``, ``save()``, and ``export()`` methods. Below is a barebones example of a custom agent implementation: @@ -74,6 +74,9 @@ Below is a barebones example of a custom agent implementation: # Call your agent's function that exports it to a transportable file format. +You will also need to modify :py:class:`primaite.primaite_session.PrimaiteSession` class to capture your new agent identifier. + +