Rcognita: A framework for DP and RL algorithm development, testing, and simulation

Welocme to rcognita’s documentation! This wiki contains all the nescessary information to get started with usage or development. Follow the installation instructions to get rcognita or check out rcognita’s gitflic page if you’d like to browse releases or fork the repository.

• About
• Installation
• What is rcognita?
• rcognita’s config pipeline
• Presets
• Related literature
• Closing remarks
• For developers

Modules

Classes

ComplementedConfig(cfg[, config_path])	A config object, generated by rcognita’s config pipeline.
main(*args[, logger, callbacks])	The decorator used to invoke rcognita’s config pipeline.

rcognita.actors	This module contains actors, i.e., entities that directly calculate actions.
rcognita.callbacks	This module contains callbacks.
rcognita.controllers	This module contains high-level structures of controllers (agents).
rcognita.critics	This module containing critics, which are integrated in controllers (agents).
rcognita.loggers	This module contains the logger interface along with concrete realizations for each separate system.
rcognita.models	This module contains model classes.
rcognita.objectives	Module that contains general objectives functions that can be used by various entities of the framework.
rcognita.observers
rcognita.optimizers	This module contains optimization routines to be used in optimal controllers, actors, critics etc.
rcognita.predictors	Module that contains state or observation (depending on the context) predictors.
rcognita.scenarios	This module contains various simulation scenarios.
rcognita.simulator	This module contains one single class that simulates controller-system (agent-environment) loops.
rcognita.solvers
rcognita.systems	This module contains a generic interface for systems (environments) as well as concrete systems as realizations of the former
rcognita.visualization