rcognita.controllers

This module contains controllers (agents).

Remarks:

  • All vectors are treated as of type [n,]

  • All buffers are treated as of type [L, n] where each row is a vector

  • Buffers are updated from bottom to top

Functions

ctrl_selector(t, observation, action_manual, …)

Main interface for various controllers.

Classes

CtrlNominal3WRobot(m, I[, ctrl_gain, …])

This is a class of nominal controllers for 3-wheel robots used for benchmarking of other controllers.

CtrlNominal3WRobotNI([ctrl_gain, ctrl_bnds, …])

Nominal parking controller for NI using disassembled subgradients.

CtrlOptPred(dim_input, dim_output[, mode, …])

Class of predictive optimal controllers, primarily model-predictive control and predictive reinforcement learning, that optimize a finite-horizon cost.

CtrlRLStab(dim_input, dim_output[, mode, …])

Class of reinforcement learning agents with stabilizing constraints.